ValueError: Variable ppo2_model/pi/mlp_fc0/w/Adam/ already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope?

[MatPoliquin]

When running in openai_ppo
python3 ./run.py --bsuite_id=SWEEP

I get this error:
ValueError: Variable ppo2_model/pi/mlp_fc0/w/Adam/ already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope?

I ran test.sh and all the tests passes

• python 3.6
• tensorflow 1.14
• Ubuntu 18.10

Here is the log:

`
[Last finished: bandit/15]: 3%|███▋ | 15/468 [34:10<88:11:07, 700.81s/it]concurrent.futures.process._RemoteTraceback:
"""
Traceback (most recent call last):
File "/usr/lib/python3.6/concurrent/futures/process.py", line 175, in _process_worker
r = call_item.fn(*call_item.args, **call_item.kwargs)
File "/usr/lib/python3.6/concurrent/futures/process.py", line 153, in _process_chunk
return [fn(*args) for args in chunk]
File "/usr/lib/python3.6/concurrent/futures/process.py", line 153, in
return [fn(*args) for args in chunk]
File "./run.py", line 81, in run
gamma=FLAGS.agent_discount,
File "/home/amdfanboy/github/baselines-youtube/baselines/ppo2/ppo2.py", line 108, in learn
File "/home/amdfanboy/github/baselines-youtube/baselines/ppo2/model.py", line 111, in init
File "/home/amdfanboy/vbsuite/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 595, in apply_gradients
self._create_slots(var_list)
File "/home/amdfanboy/vbsuite/lib/python3.6/site-packages/tensorflow/python/training/adam.py", line 135, in _create_slots
self._zeros_slot(v, "m", self._name)
File "/home/amdfanboy/vbsuite/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 1153, in _zeros_slot
new_slot_variable = slot_creator.create_zeros_slot(var, op_name)
File "/home/amdfanboy/vbsuite/lib/python3.6/site-packages/tensorflow/python/training/slot_creator.py", line 183, in create_zeros_slot
colocate_with_primary=colocate_with_primary)
File "/home/amdfanboy/vbsuite/lib/python3.6/site-packages/tensorflow/python/training/slot_creator.py", line 157, in create_slot_with_initializer
dtype)
File "/home/amdfanboy/vbsuite/lib/python3.6/site-packages/tensorflow/python/training/slot_creator.py", line 65, in _create_slot_var
validate_shape=validate_shape)
File "/home/amdfanboy/vbsuite/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 1479, in get_variable
aggregation=aggregation)
File "/home/amdfanboy/vbsuite/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 1220, in get_variable
aggregation=aggregation)
File "/home/amdfanboy/vbsuite/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 547, in get_variable
aggregation=aggregation)
File "/home/amdfanboy/vbsuite/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 499, in _true_getter
aggregation=aggregation)
File "/home/amdfanboy/vbsuite/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 848, in _get_single_variable
traceback.format_list(tb))))
ValueError: Variable ppo2_model/pi/mlp_fc0/w/Adam/ already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at:

File "/home/amdfanboy/github/baselines-youtube/baselines/ppo2/model.py", line 111, in init
File "/home/amdfanboy/github/baselines-youtube/baselines/ppo2/ppo2.py", line 108, in learn
File "./run.py", line 81, in run
gamma=FLAGS.agent_discount,

"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "./run.py", line 107, in
app.run(main)
File "/home/amdfanboy/.local/lib/python3.6/site-packages/absl/app.py", line 300, in run
_run_main(main, args)
File "/home/amdfanboy/.local/lib/python3.6/site-packages/absl/app.py", line 251, in _run_main
sys.exit(main(argv))
File "./run.py", line 100, in main
pool.map_mpi(run, bsuite_sweep)
File "/home/amdfanboy/github/bsuite/bsuite/baselines/utils/pool.py", line 53, in map_mpi
for bsuite_id in pool.map(run_fn, bsuite_ids):
File "/usr/lib/python3.6/concurrent/futures/process.py", line 366, in _chain_from_iterable_of_lists
for element in iterable:
File "/usr/lib/python3.6/concurrent/futures/_base.py", line 586, in result_iterator
yield fs.pop().result()
File "/usr/lib/python3.6/concurrent/futures/_base.py", line 425, in result
return self.__get_result()
File "/usr/lib/python3.6/concurrent/futures/_base.py", line 384, in __get_result
raise self._exception
ValueError: Variable ppo2_model/pi/mlp_fc0/w/Adam/ already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at:

File "/home/amdfanboy/github/baselines-youtube/baselines/ppo2/model.py", line 111, in init
File "/home/amdfanboy/github/baselines-youtube/baselines/ppo2/ppo2.py", line 108, in learn
File "./run.py", line 81, in run
gamma=FLAGS.agent_discount,

`

[iosband]

Hi there - I've had a look at this and can't reproduce that behaviour.

My guess is that your OpenAI baselines:
"/home/amdfanboy/github/baselines-youtube/baselines/ppo2/ppo2.py"

Does not match the OpenAI baselines this script is meant to run:
https://github.com/openai/baselines

I can confirm that if you follow the installation instructions from a fresh workspace you will be able to run the script successfully.
Feel free to re-open if that is not the case.

Thanks!