/home/shenk/micromamba/envs/marllib/bin/python /home/shenk/HW/FQW2/hai-nonconflict-action-learning/runners/run_marllib.py +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | Env_Name | Check_Status | Error_Log | Config_File_Location | Env_File_Location | +====================+================+========================================================================================================================================================================+==============================================+=====================================+ | gymnasium_mamujoco | Error | No module named 'gymnasium_robotics' | envs/base_env/config/gymnasium_mamujoco.yaml | envs/base_env/gymnasium_mamujoco.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | mpe | Ready | Null | envs/base_env/config/mpe.yaml | envs/base_env/mpe.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | gymnasium_mpe | Ready | Null | envs/base_env/config/gymnasium_mpe.yaml | envs/base_env/gymnasium_mpe.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | mamujoco | Error | No module named 'multiagent_mujoco' | envs/base_env/config/mamujoco.yaml | envs/base_env/mamujoco.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | smac | Error | No module named 'smac' | envs/base_env/config/smac.yaml | envs/base_env/smac.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | football | Error | No module named 'gfootball' | envs/base_env/config/football.yaml | envs/base_env/football.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | magent | Error | MAgent has been moved into its own package: MAgent2. Install with `pip install magent2`. For more information on the MAgent2 package, see https://magent2.farama.org/. | envs/base_env/config/magent.yaml | envs/base_env/magent.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | rware | Error | No module named 'rware' | envs/base_env/config/rware.yaml | envs/base_env/rware.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | lbf | Error | No module named 'lbforaging' | envs/base_env/config/lbf.yaml | envs/base_env/lbf.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | pommerman | Error | No module named 'pommerman' | envs/base_env/config/pommerman.yaml | envs/base_env/pommerman.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | hanabi | Error | No module named 'cffi' | envs/base_env/config/hanabi.yaml | envs/base_env/hanabi.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | metadrive | Error | No module named 'metadrive' | envs/base_env/config/metadrive.yaml | envs/base_env/metadrive.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | mate | Error | No module named 'mate' | envs/base_env/config/mate.yaml | envs/base_env/mate.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | gobigger | Error | No module named 'gobigger' | envs/base_env/config/gobigger.yaml | envs/base_env/gobigger.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | overcooked | Error | No module named 'overcooked_ai_py' | envs/base_env/config/overcooked.yaml | envs/base_env/overcooked.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | voltage | Error | No module named 'pandapower' | envs/base_env/config/voltage.yaml | envs/base_env/voltage.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | aircombat | Error | No module named 'jsbsim' | envs/base_env/config/aircombat.yaml | envs/base_env/aircombat.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | hns | Error | No module named 'mujoco_worldgen' | envs/base_env/config/hns.yaml | envs/base_env/hns.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | sisl | Ready | Null | envs/base_env/config/sisl.yaml | envs/base_env/sisl.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ /home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/pettingzoo/utils/conversions.py:142: UserWarning: The `action_spaces` dictionary is deprecated. Use the `action_space` function instead. warnings.warn( /home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/pettingzoo/utils/conversions.py:128: UserWarning: The `observation_spaces` dictionary is deprecated. Use the `observation_space` function instead. warnings.warn( 2024-02-08 13:58:30,160 WARNING sample.py:401 -- DeprecationWarning: wrapping . at 0x7fef02095670> with tune.function() is no longer needed 2024-02-08 13:58:30,350 WARNING worker.py:496 -- `ray.get_gpu_ids()` will always return the empty list when called from the driver. This is because Ray does not manage GPU allocations to the driver process. :task_name:bundle_reservation_check_func :actor_name:HAPPOTrainer 2024-02-08 13:58:30,473 WARNING deprecation.py:38 -- DeprecationWarning: `simple_optimizer` has been deprecated. This will raise an error in the future! 2024-02-08 13:58:30,474 WARNING ppo.py:143 -- `train_batch_size` (250) cannot be achieved with your other settings (num_workers=1 num_envs_per_worker=1 rollout_fragment_length=200)! Auto-adjusting `rollout_fragment_length` to 250. 2024-02-08 13:58:30,474 INFO ppo.py:166 -- In multi-agent mode, policies will be optimized sequentially by the multi-GPU optimizer. Consider setting simple_optimizer=True if this doesn't work for you. 2024-02-08 13:58:30,474 INFO trainer.py:770 -- Current log_level is WARN. For more information, set 'log_level': 'INFO' / 'DEBUG' or use the -v and -vv flags. :actor_name:RolloutWorker /home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/torch/cuda/__init__.py:52: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 9010). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at /pytorch/c10/cuda/CUDAFunctions.cpp:115.) return torch._C._cuda_getDeviceCount() > 0 2024-02-08 13:58:30,599 WARNING deprecation.py:38 -- DeprecationWarning: `SampleBatch['is_training']` has been deprecated. Use `SampleBatch.is_training` instead. This will raise an error in the future! 2024-02-08 13:58:31,029 WARNING trainer_template.py:185 -- `execution_plan` functions should accept `trainer`, `workers`, and `config` as args! 2024-02-08 13:58:31,030 WARNING deprecation.py:38 -- DeprecationWarning: `simple_optimizer` has been deprecated. This will raise an error in the future! /home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/pettingzoo/utils/conversions.py:142: UserWarning: The `action_spaces` dictionary is deprecated. Use the `action_space` function instead. warnings.warn( /home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/pettingzoo/utils/conversions.py:128: UserWarning: The `observation_spaces` dictionary is deprecated. Use the `observation_space` function instead. warnings.warn( :actor_name:HAPPOTrainer 2024-02-08 13:58:31,082 WARNING util.py:57 -- Install gputil for GPU system monitoring. 2024-02-08 13:58:31,089 WARNING deprecation.py:38 -- DeprecationWarning: `policy_mapping_fn(agent_id)` has been deprecated. Use `policy_mapping_fn(agent_id, episode, worker, **kwargs)` instead. This will raise an error in the future! == Status == Current time: 2024-02-08 13:58:33 (running for 00:00:03.41) Memory usage on this node: 10.6/15.5 GiB Using FIFO scheduling algorithm. Resources requested: 2.0/8 CPUs, 0/0 GPUs, 0.0/4.08 GiB heap, 0.0/2.04 GiB objects (0.0/1.0 accelerator_type:GT) Result logdir: /home/shenk/HW/FQW2/hai-nonconflict-action-learning/runners/exp_results/happo_mlp_simple_spread_5e-07_0.0005_APPEND-DATA_seed-0 Number of trials: 1/1 (1 RUNNING) +------------------------------------------------------+----------+---------------------+ | Trial name | status | loc | |------------------------------------------------------+----------+---------------------| | HAPPOTrainer_gymnasium_mpe_simple_spread_fe64f_00000 | RUNNING | 192.168.1.184:61617 | +------------------------------------------------------+----------+---------------------+ == Status == Current time: 2024-02-08 13:58:39 (running for 00:00:08.91) Memory usage on this node: 10.6/15.5 GiB Using FIFO scheduling algorithm. Resources requested: 2.0/8 CPUs, 0/0 GPUs, 0.0/4.08 GiB heap, 0.0/2.04 GiB objects (0.0/1.0 accelerator_type:GT) Result logdir: /home/shenk/HW/FQW2/hai-nonconflict-action-learning/runners/exp_results/happo_mlp_simple_spread_5e-07_0.0005_APPEND-DATA_seed-0 Number of trials: 1/1 (1 RUNNING) +------------------------------------------------------+----------+---------------------+--------+------------------+------+----------+----------------------+----------------------+--------------------+ | Trial name | status | loc | iter | total time (s) | ts | reward | episode_reward_max | episode_reward_min | episode_len_mean | |------------------------------------------------------+----------+---------------------+--------+------------------+------+----------+----------------------+----------------------+--------------------| | HAPPOTrainer_gymnasium_mpe_simple_spread_fe64f_00000 | RUNNING | 192.168.1.184:61617 | 2 | 5.22131 | 500 | -73.7634 | -45.0337 | -108.397 | 25 | +------------------------------------------------------+----------+---------------------+--------+------------------+------+----------+----------------------+----------------------+--------------------+ == Status == Current time: 2024-02-08 13:58:42 (running for 00:00:12.46) Memory usage on this node: 10.6/15.5 GiB Using FIFO scheduling algorithm. Resources requested: 0/8 CPUs, 0/0 GPUs, 0.0/4.08 GiB heap, 0.0/2.04 GiB objects (0.0/1.0 accelerator_type:GT) Result logdir: /home/shenk/HW/FQW2/hai-nonconflict-action-learning/runners/exp_results/happo_mlp_simple_spread_5e-07_0.0005_APPEND-DATA_seed-0 Number of trials: 1/1 (1 TERMINATED) +------------------------------------------------------+------------+---------------------+--------+------------------+------+----------+----------------------+----------------------+--------------------+ | Trial name | status | loc | iter | total time (s) | ts | reward | episode_reward_max | episode_reward_min | episode_len_mean | |------------------------------------------------------+------------+---------------------+--------+------------------+------+----------+----------------------+----------------------+--------------------| | HAPPOTrainer_gymnasium_mpe_simple_spread_fe64f_00000 | TERMINATED | 192.168.1.184:61617 | 4 | 10.4356 | 1000 | -76.8308 | -45.0337 | -123.001 | 25 | +------------------------------------------------------+------------+---------------------+--------+------------------+------+----------+----------------------+----------------------+--------------------+ 2024-02-08 13:58:42,794 INFO tune.py:630 -- Total run time: 12.63 seconds (12.09 seconds for the tuning loop). +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | Env_Name | Check_Status | Error_Log | Config_File_Location | Env_File_Location | +====================+================+========================================================================================================================================================================+==============================================+=====================================+ | gymnasium_mamujoco | Error | No module named 'gymnasium_robotics' | envs/base_env/config/gymnasium_mamujoco.yaml | envs/base_env/gymnasium_mamujoco.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | mpe | Ready | Null | envs/base_env/config/mpe.yaml | envs/base_env/mpe.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | gymnasium_mpe | Ready | Null | envs/base_env/config/gymnasium_mpe.yaml | envs/base_env/gymnasium_mpe.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | mamujoco | Error | No module named 'multiagent_mujoco' | envs/base_env/config/mamujoco.yaml | envs/base_env/mamujoco.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | smac | Error | No module named 'smac' | envs/base_env/config/smac.yaml | envs/base_env/smac.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | football | Error | No module named 'gfootball' | envs/base_env/config/football.yaml | envs/base_env/football.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | magent | Error | MAgent has been moved into its own package: MAgent2. Install with `pip install magent2`. For more information on the MAgent2 package, see https://magent2.farama.org/. | envs/base_env/config/magent.yaml | envs/base_env/magent.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | rware | Error | No module named 'rware' | envs/base_env/config/rware.yaml | envs/base_env/rware.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | lbf | Error | No module named 'lbforaging' | envs/base_env/config/lbf.yaml | envs/base_env/lbf.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | pommerman | Error | No module named 'pommerman' | envs/base_env/config/pommerman.yaml | envs/base_env/pommerman.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | hanabi | Error | No module named 'cffi' | envs/base_env/config/hanabi.yaml | envs/base_env/hanabi.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | metadrive | Error | No module named 'metadrive' | envs/base_env/config/metadrive.yaml | envs/base_env/metadrive.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | mate | Error | No module named 'mate' | envs/base_env/config/mate.yaml | envs/base_env/mate.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | gobigger | Error | No module named 'gobigger' | envs/base_env/config/gobigger.yaml | envs/base_env/gobigger.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | overcooked | Error | No module named 'overcooked_ai_py' | envs/base_env/config/overcooked.yaml | envs/base_env/overcooked.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | voltage | Error | No module named 'pandapower' | envs/base_env/config/voltage.yaml | envs/base_env/voltage.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | aircombat | Error | No module named 'jsbsim' | envs/base_env/config/aircombat.yaml | envs/base_env/aircombat.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | hns | Error | No module named 'mujoco_worldgen' | envs/base_env/config/hns.yaml | envs/base_env/hns.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ | sisl | Ready | Null | envs/base_env/config/sisl.yaml | envs/base_env/sisl.py | +--------------------+----------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------+-------------------------------------+ /home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/pettingzoo/utils/conversions.py:142: UserWarning: The `action_spaces` dictionary is deprecated. Use the `action_space` function instead. warnings.warn( /home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/pettingzoo/utils/conversions.py:128: UserWarning: The `observation_spaces` dictionary is deprecated. Use the `observation_space` function instead. warnings.warn( 2024-02-08 13:58:46,370 WARNING sample.py:401 -- DeprecationWarning: wrapping . at 0x7fef85f6c0d0> with tune.function() is no longer needed :task_name:bundle_reservation_check_func :actor_name:HATRPOTrainer 2024-02-08 13:58:46,627 WARNING deprecation.py:38 -- DeprecationWarning: `simple_optimizer` has been deprecated. This will raise an error in the future! 2024-02-08 13:58:46,628 WARNING ppo.py:143 -- `train_batch_size` (250) cannot be achieved with your other settings (num_workers=1 num_envs_per_worker=1 rollout_fragment_length=200)! Auto-adjusting `rollout_fragment_length` to 250. :actor_name:RolloutWorker /home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/torch/autograd/__init__.py:226: UserWarning: Error detected in MulBackward0. Traceback of forward call that caused the error: File "/home/shenk/HW/FQW2/hai-nonconflict-action-learning/runners/run_marllib.py", line 11, in algo.fit(env, model, stop={'timesteps_total': 1000}) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/__init__.py", line 316, in fit return run_cc(self.config_dict, env_instance, model_class, stop=stop) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/run_cc.py", line 194, in run_cc results = POlICY_REGISTRY[exp_info["algorithm"]](model, exp_info, run_config, env_info, stop_config, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/scripts/hatrpo.py", line 121, in run_hatrpo results = tune.run(HATRPOTrainer, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/tune.py", line 601, in run runner.step() File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trial_runner.py", line 689, in step if _start_trial(next_trial): File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trial_runner.py", line 679, in _start_trial if self.trial_executor.start_trial(trial): File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/ray_trial_executor.py", line 611, in start_trial return self._start_trial(trial, checkpoint, train=train) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/ray_trial_executor.py", line 486, in _start_trial runner = self._setup_remote_runner(trial) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/ray_trial_executor.py", line 403, in _setup_remote_runner return full_actor_class.remote(**kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/actor.py", line 486, in remote return actor_cls._remote( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 371, in _invocation_actor_class_remote_span return method(self, args, kwargs, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/actor.py", line 746, in _remote actor_id = worker.core_worker.create_actor( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/_private/function_manager.py", line 576, in actor_method_executor return method(__ray_actor, *args, **kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 451, in _resume_span return method(self, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 137, in __init__ Trainer.__init__(self, config, env, logger_creator) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 623, in __init__ super().__init__(config, logger_creator) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trainable.py", line 107, in __init__ self.setup(copy.deepcopy(self.config)) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 451, in _resume_span return method(self, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 147, in setup super().setup(config) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 776, in setup self._init(self.config, self.env_creator) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 451, in _resume_span return method(self, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 171, in _init self.workers = self._make_workers( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 451, in _resume_span return method(self, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 858, in _make_workers return WorkerSet( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/worker_set.py", line 78, in __init__ self.add_workers(num_workers) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/worker_set.py", line 149, in add_workers self._remote_workers.extend([ File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/worker_set.py", line 150, in self._make_worker( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/worker_set.py", line 406, in _make_worker worker = cls( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/actor.py", line 437, in remote return self._remote(args=args, kwargs=kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 371, in _invocation_actor_class_remote_span return method(self, args, kwargs, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/actor.py", line 746, in _remote actor_id = worker.core_worker.create_actor( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/_private/function_manager.py", line 576, in actor_method_executor return method(__ray_actor, *args, **kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 451, in _resume_span return method(self, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 584, in __init__ self._build_policy_map( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 451, in _resume_span return method(self, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 1384, in _build_policy_map self.policy_map.create_policy(name, orig_cls, obs_space, act_space, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy_map.py", line 143, in create_policy self[policy_id] = class_(observation_space, action_space, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy_template.py", line 280, in __init__ self._initialize_loss_from_dummy_batch( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy.py", line 774, in _initialize_loss_from_dummy_batch self._loss(self, self.model, self.dist_class, train_batch) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/core/CC/hatrpo.py", line 160, in hatrpo_loss_fn trust_region_updator.update(update_critic=False) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 154, in update self.update_actor(self.initialize_policy_loss) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 174, in update_actor step_dir = self.conjugate_gradients( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 140, in conjugate_gradients _Avp = self.fisher_vector_product(p) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 129, in fisher_vector_product kl_grad_p = (kl_grads * p).sum() (Triggered internally at /pytorch/torch/csrc/autograd/python_anomaly_mode.cpp:104.) return Variable._execution_engine.run_backward( [2024-02-08 13:58:46,939 E 61617 61617] core_worker.cc:1561: Pushed Error with JobID: 01000000 of type: task with message: ray::RolloutWorker.__init__() (pid=61617, ip=192.168.1.184, repr=.Class object at 0x7fef85ea6580>) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 584, in __init__ self._build_policy_map( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 1384, in _build_policy_map self.policy_map.create_policy(name, orig_cls, obs_space, act_space, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy_map.py", line 143, in create_policy self[policy_id] = class_(observation_space, action_space, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy_template.py", line 280, in __init__ self._initialize_loss_from_dummy_batch( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy.py", line 774, in _initialize_loss_from_dummy_batch self._loss(self, self.model, self.dist_class, train_batch) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/core/CC/hatrpo.py", line 160, in hatrpo_loss_fn trust_region_updator.update(update_critic=False) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 154, in update self.update_actor(self.initialize_policy_loss) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 174, in update_actor step_dir = self.conjugate_gradients( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 140, in conjugate_gradients _Avp = self.fisher_vector_product(p) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 130, in fisher_vector_product kl_hessian_p = torch.autograd.grad(kl_grad_p, self.actor_parameters, allow_unused=True) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/torch/autograd/__init__.py", line 226, in grad return Variable._execution_engine.run_backward( RuntimeError: Function 'MulBackward0' returned nan values in its 0th output. at time: 1.70739e+09 2024-02-08 13:58:46,940 ERROR actor.py:746 -- Exception raised in creation task: The actor died because of an error raised in its creation task, ray::RolloutWorker.__init__() (pid=61617, ip=192.168.1.184) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 584, in __init__ self._build_policy_map( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 1384, in _build_policy_map self.policy_map.create_policy(name, orig_cls, obs_space, act_space, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy_map.py", line 143, in create_policy self[policy_id] = class_(observation_space, action_space, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy_template.py", line 280, in __init__ self._initialize_loss_from_dummy_batch( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy.py", line 774, in _initialize_loss_from_dummy_batch self._loss(self, self.model, self.dist_class, train_batch) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/core/CC/hatrpo.py", line 160, in hatrpo_loss_fn trust_region_updator.update(update_critic=False) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 154, in update self.update_actor(self.initialize_policy_loss) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 174, in update_actor step_dir = self.conjugate_gradients( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 140, in conjugate_gradients _Avp = self.fisher_vector_product(p) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 130, in fisher_vector_product kl_hessian_p = torch.autograd.grad(kl_grad_p, self.actor_parameters, allow_unused=True) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/torch/autograd/__init__.py", line 226, in grad return Variable._execution_engine.run_backward( RuntimeError: Function 'MulBackward0' returned nan values in its 0th output. [2024-02-08 13:58:46,947 E 61617 61617] core_worker.cc:1561: Pushed Error with JobID: 01000000 of type: task with message: ray::RolloutWorker.foreach_env()::Exiting (pid=61617, ip=192.168.1.184, repr=.Class object at 0x7fef85ea6580>) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 1018, in foreach_env if self.async_env is None: AttributeError: 'RolloutWorker' object has no attribute 'async_env' at time: 1.70739e+09 /home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/torch/autograd/__init__.py:226: UserWarning: Error detected in MulBackward0. Traceback of forward call that caused the error: File "/home/shenk/HW/FQW2/hai-nonconflict-action-learning/runners/run_marllib.py", line 11, in algo.fit(env, model, stop={'timesteps_total': 1000}) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/__init__.py", line 316, in fit return run_cc(self.config_dict, env_instance, model_class, stop=stop) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/run_cc.py", line 194, in run_cc results = POlICY_REGISTRY[exp_info["algorithm"]](model, exp_info, run_config, env_info, stop_config, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/scripts/hatrpo.py", line 121, in run_hatrpo results = tune.run(HATRPOTrainer, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/tune.py", line 601, in run runner.step() File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trial_runner.py", line 689, in step if _start_trial(next_trial): File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trial_runner.py", line 679, in _start_trial if self.trial_executor.start_trial(trial): File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/ray_trial_executor.py", line 611, in start_trial return self._start_trial(trial, checkpoint, train=train) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/ray_trial_executor.py", line 486, in _start_trial runner = self._setup_remote_runner(trial) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/ray_trial_executor.py", line 403, in _setup_remote_runner return full_actor_class.remote(**kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/actor.py", line 486, in remote return actor_cls._remote( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 371, in _invocation_actor_class_remote_span return method(self, args, kwargs, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/actor.py", line 746, in _remote actor_id = worker.core_worker.create_actor( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/_private/function_manager.py", line 576, in actor_method_executor return method(__ray_actor, *args, **kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 451, in _resume_span return method(self, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 137, in __init__ Trainer.__init__(self, config, env, logger_creator) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 623, in __init__ super().__init__(config, logger_creator) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trainable.py", line 107, in __init__ self.setup(copy.deepcopy(self.config)) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 451, in _resume_span return method(self, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 147, in setup super().setup(config) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 776, in setup self._init(self.config, self.env_creator) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 451, in _resume_span return method(self, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 171, in _init self.workers = self._make_workers( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/util/tracing/tracing_helper.py", line 451, in _resume_span return method(self, *_args, **_kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 858, in _make_workers return WorkerSet( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/worker_set.py", line 110, in __init__ self._local_worker = self._make_worker( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/worker_set.py", line 406, in _make_worker worker = cls( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 584, in __init__ self._build_policy_map( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 1384, in _build_policy_map self.policy_map.create_policy(name, orig_cls, obs_space, act_space, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy_map.py", line 143, in create_policy self[policy_id] = class_(observation_space, action_space, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy_template.py", line 280, in __init__ self._initialize_loss_from_dummy_batch( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy.py", line 774, in _initialize_loss_from_dummy_batch self._loss(self, self.model, self.dist_class, train_batch) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/core/CC/hatrpo.py", line 160, in hatrpo_loss_fn trust_region_updator.update(update_critic=False) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 154, in update self.update_actor(self.initialize_policy_loss) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 174, in update_actor step_dir = self.conjugate_gradients( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 140, in conjugate_gradients _Avp = self.fisher_vector_product(p) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 129, in fisher_vector_product kl_grad_p = (kl_grads * p).sum() (Triggered internally at /pytorch/torch/csrc/autograd/python_anomaly_mode.cpp:104.) return Variable._execution_engine.run_backward( [2024-02-08 13:58:47,107 E 61617 61617] core_worker.cc:1561: Pushed Error with JobID: 01000000 of type: task with message: ray::HATRPOTrainer.__init__() (pid=61617, ip=192.168.1.184, repr=HATRPOTrainer) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 137, in __init__ Trainer.__init__(self, config, env, logger_creator) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 623, in __init__ super().__init__(config, logger_creator) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trainable.py", line 107, in __init__ self.setup(copy.deepcopy(self.config)) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 147, in setup super().setup(config) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 776, in setup self._init(self.config, self.env_creator) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 171, in _init self.workers = self._make_workers( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 858, in _make_workers return WorkerSet( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/worker_set.py", line 110, in __init__ self._local_worker = self._make_worker( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/worker_set.py", line 406, in _make_worker worker = cls( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 584, in __init__ self._build_policy_map( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 1384, in _build_policy_map self.policy_map.create_policy(name, orig_cls, obs_space, act_space, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy_map.py", line 143, in create_policy self[policy_id] = class_(observation_space, action_space, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy_template.py", line 280, in __init__ self._initialize_loss_from_dummy_batch( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy.py", line 774, in _initialize_loss_from_dummy_batch self._loss(self, self.model, self.dist_class, train_batch) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/core/CC/hatrpo.py", line 160, in hatrpo_loss_fn trust_region_updator.update(update_critic=False) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 154, in update self.update_actor(self.initialize_policy_loss) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 174, in update_actor step_dir = self.conjugate_gradients( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 140, in conjugate_gradients _Avp = self.fisher_vector_product(p) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 130, in fisher_vector_product kl_hessian_p = torch.autograd.grad(kl_grad_p, self.actor_parameters, allow_unused=True) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/torch/autograd/__init__.py", line 226, in grad return Variable._execution_engine.run_backward( RuntimeError: Function 'MulBackward0' returned nan values in its 0th output. at time: 1.70739e+09 2024-02-08 13:58:47,108 ERROR actor.py:746 -- Exception raised in creation task: The actor died because of an error raised in its creation task, ray::HATRPOTrainer.__init__() (pid=61617, ip=192.168.1.184) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 137, in __init__ Trainer.__init__(self, config, env, logger_creator) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 623, in __init__ super().__init__(config, logger_creator) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trainable.py", line 107, in __init__ self.setup(copy.deepcopy(self.config)) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 147, in setup super().setup(config) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 776, in setup self._init(self.config, self.env_creator) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 171, in _init self.workers = self._make_workers( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 858, in _make_workers return WorkerSet( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/worker_set.py", line 110, in __init__ self._local_worker = self._make_worker( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/worker_set.py", line 406, in _make_worker worker = cls( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 584, in __init__ self._build_policy_map( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/evaluation/rollout_worker.py", line 1384, in _build_policy_map self.policy_map.create_policy(name, orig_cls, obs_space, act_space, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy_map.py", line 143, in create_policy self[policy_id] = class_(observation_space, action_space, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy_template.py", line 280, in __init__ self._initialize_loss_from_dummy_batch( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/policy/policy.py", line 774, in _initialize_loss_from_dummy_batch self._loss(self, self.model, self.dist_class, train_batch) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/core/CC/hatrpo.py", line 160, in hatrpo_loss_fn trust_region_updator.update(update_critic=False) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 154, in update self.update_actor(self.initialize_policy_loss) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 174, in update_actor step_dir = self.conjugate_gradients( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 140, in conjugate_gradients _Avp = self.fisher_vector_product(p) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/utils/trust_regions.py", line 130, in fisher_vector_product kl_hessian_p = torch.autograd.grad(kl_grad_p, self.actor_parameters, allow_unused=True) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/torch/autograd/__init__.py", line 226, in grad return Variable._execution_engine.run_backward( RuntimeError: Function 'MulBackward0' returned nan values in its 0th output. [2024-02-08 13:58:47,113 E 61617 61617] core_worker.cc:1561: Pushed Error with JobID: 01000000 of type: task with message: ray::HATRPOTrainer.get_auto_filled_metrics()::Exiting (pid=61617, ip=192.168.1.184, repr=HATRPOTrainer) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trainable.py", line 179, in get_auto_filled_metrics NODE_IP: self._local_ip, AttributeError: 'HATRPOTrainer' object has no attribute '_local_ip' at time: 1.70739e+09 [2024-02-08 13:58:47,615 E 61617 61617] core_worker.cc:1561: Pushed Error with JobID: 01000000 of type: task with message: ray::HATRPOTrainer.train()::Exiting (pid=61617, ip=192.168.1.184, repr=HATRPOTrainer) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 682, in train raise e File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer.py", line 668, in train result = Trainable.train(self) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trainable.py", line 283, in train result = self.step() File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/rllib/agents/trainer_template.py", line 206, in step step_results = next(self.train_exec_impl) AttributeError: 'HATRPOTrainer' object has no attribute 'train_exec_impl' at time: 1.70739e+09 Traceback (most recent call last): File "/home/shenk/HW/FQW2/hai-nonconflict-action-learning/runners/run_marllib.py", line 11, in algo.fit(env, model, stop={'timesteps_total': 1000}) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/__init__.py", line 316, in fit return run_cc(self.config_dict, env_instance, model_class, stop=stop) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/run_cc.py", line 194, in run_cc results = POlICY_REGISTRY[exp_info["algorithm"]](model, exp_info, run_config, env_info, stop_config, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/marllib/marl/algos/scripts/hatrpo.py", line 121, in run_hatrpo results = tune.run(HATRPOTrainer, File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/tune.py", line 603, in run _report_progress(runner, progress_reporter) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/tune.py", line 68, in _report_progress reporter.report(trials, done, sched_debug_str, executor_debug_str) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/progress_reporter.py", line 520, in report print(self._progress_str(trials, done, *sys_info)) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/progress_reporter.py", line 279, in _progress_str user_metrics = self._infer_user_metrics(trials, self._infer_limit) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/progress_reporter.py", line 325, in _infer_user_metrics if not t.last_result: File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trial.py", line 433, in last_result self._get_default_result_or_future() File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trial.py", line 409, in _get_default_result_or_future self._default_result_or_future = ray.get( File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/_private/client_mode_hook.py", line 105, in wrapper return func(*args, **kwargs) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/worker.py", line 1625, in get raise value.as_instanceof_cause() ray.exceptions.RayTaskError(AttributeError): ray::HATRPOTrainer.get_auto_filled_metrics()::Exiting (pid=61617, ip=192.168.1.184, repr=HATRPOTrainer) File "/home/shenk/micromamba/envs/marllib/lib/python3.9/site-packages/ray/tune/trainable.py", line 179, in get_auto_filled_metrics NODE_IP: self._local_ip, AttributeError: 'HATRPOTrainer' object has no attribute '_local_ip' Process finished with exit code 1