All algorithm are derived from nnabla_rl.algorithm.Algorithm
.
Note
Algorithm will run on cpu by default (No matter what nnabla context is set in prior to the instantiation). If you want to run the algorithm on gpu, set the gpu_id through the algorithm's config. Note that the algorithm will override the nnabla context when the training starts.
nnabla_rl.algorithm.AlgorithmConfig
nnabla_rl.algorithm.Algorithm
nnabla_rl.algorithms.a2c.A2CConfig
nnabla_rl.algorithms.a2c.A2C
nnabla_rl.algorithms.atrpo.ATRPOConfig
nnabla_rl.algorithms.atrpo.ATRPO
nnabla_rl.algorithms.bcq.BCQConfig
nnabla_rl.algorithms.bcq.BCQ
nnabla_rl.algorithms.bear.BEARConfig
nnabla_rl.algorithms.bear.BEAR
nnabla_rl.algorithms.categorical_ddqn.CategoricalDDQNConfig
nnabla_rl.algorithms.categorical_ddqn.CategoricalDDQN
nnabla_rl.algorithms.categorical_dqn.CategoricalDQNConfig
nnabla_rl.algorithms.categorical_dqn.CategoricalDQN
nnabla_rl.algorithms.ddp.DDPConfig
nnabla_rl.algorithms.ddp.DDP
nnabla_rl.algorithms.ddpg.DDPGConfig
nnabla_rl.algorithms.ddpg.DDPG
nnabla_rl.algorithms.ddqn.DDQNConfig
nnabla_rl.algorithms.ddqn.DDQN
DecisionTransformer ===== .. autoclass:: nnabla_rl.algorithms.decision_transformer.DecisionTransformerConfig :members: :show-inheritance:
nnabla_rl.algorithms.decision_transformer.DecisionTransformer
nnabla_rl.algorithms.dqn.DQNConfig
nnabla_rl.algorithms.dqn.DQN
nnabla_rl.algorithms.drqn.DRQNConfig
nnabla_rl.algorithms.drqn.DRQN
nnabla_rl.algorithms.gail.GAILConfig
nnabla_rl.algorithms.gail.GAIL
nnabla_rl.algorithms.her.HERConfig
nnabla_rl.algorithms.her.HER
nnabla_rl.algorithms.ilqr.iLQRConfig
nnabla_rl.algorithms.ilqr.iLQR
nnabla_rl.algorithms.iqn.IQNConfig
nnabla_rl.algorithms.iqn.IQN
nnabla_rl.algorithms.lqr.LQRConfig
nnabla_rl.algorithms.lqr.LQR
nnabla_rl.algorithms.mme_sac.MMESACConfig
nnabla_rl.algorithms.mme_sac.MMESAC
MMESAC (Disentangled) =============== .. autoclass:: nnabla_rl.algorithms.demme_sac.DEMMESACConfig :members: :show-inheritance:
nnabla_rl.algorithms.demme_sac.DEMMESAC
nnabla_rl.algorithms.mppi.MPPIConfig
nnabla_rl.algorithms.mppi.MPPI
nnabla_rl.algorithms.munchausen_dqn.MunchausenDQNConfig
nnabla_rl.algorithms.munchausen_dqn.MunchausenDQN
nnabla_rl.algorithms.munchausen_iqn.MunchausenIQNConfig
nnabla_rl.algorithms.munchausen_iqn.MunchausenIQN
nnabla_rl.algorithms.ppo.PPOConfig
nnabla_rl.algorithms.ppo.PPO
nnabla_rl.algorithms.qrdqn.QRDQNConfig
nnabla_rl.algorithms.qrdqn.QRDQN
nnabla_rl.algorithms.qrsac.QRSACConfig
nnabla_rl.algorithms.qrsac.QRSAC
nnabla_rl.algorithms.icra2018_qtopt.ICRA2018QtOpt
nnabla_rl.algorithms.icra2018_qtopt.ICRA2018QtOpt
nnabla_rl.algorithms.rainbow.RainbowConfig
nnabla_rl.algorithms.rainbow.Rainbow
nnabla_rl.algorithms.reinforce.REINFORCEConfig
nnabla_rl.algorithms.reinforce.REINFORCE
nnabla_rl.algorithms.sac.SACConfig
nnabla_rl.algorithms.sac.SAC
nnabla_rl.algorithms.icml2018_sac.ICML2018SACConfig
nnabla_rl.algorithms.icml2018_sac.ICML2018SAC
SAC-D ==== .. autoclass:: nnabla_rl.algorithms.sac.SACDConfig :members: :show-inheritance:
nnabla_rl.algorithms.sacd.SACD
nnabla_rl.algorithms.td3.TD3Config
nnabla_rl.algorithms.td3.TD3
nnabla_rl.algorithms.trpo.TRPOConfig
nnabla_rl.algorithms.trpo.TRPO
nnabla_rl.algorithms.icml2015_trpo.ICML2015TRPOConfig
nnabla_rl.algorithms.icml2015_trpo.ICML2015TRPO
XQL (eXtreme Q-Learning) ===== .. autoclass:: nnabla_rl.algorithms.xql.XQLConfig :members: :show-inheritance:
nnabla_rl.algorithms.xql.XQL