Skip to content

Latest commit

 

History

History
202 lines (160 loc) · 4.12 KB

algorithms.rst

File metadata and controls

202 lines (160 loc) · 4.12 KB

Algorithms

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.

Algorithm

nnabla_rl.algorithm.AlgorithmConfig

nnabla_rl.algorithm.Algorithm

A2C

nnabla_rl.algorithms.a2c.A2CConfig

nnabla_rl.algorithms.a2c.A2C

BCQ

nnabla_rl.algorithms.bcq.BCQConfig

nnabla_rl.algorithms.bcq.BCQ

BEAR

nnabla_rl.algorithms.bear.BEARConfig

nnabla_rl.algorithms.bear.BEAR

Categorical DQN

nnabla_rl.algorithms.categorical_dqn.CategoricalDQNConfig

nnabla_rl.algorithms.categorical_dqn.CategoricalDQN

DDPG

nnabla_rl.algorithms.ddpg.DDPGConfig

nnabla_rl.algorithms.ddpg.DDPG

DQN

nnabla_rl.algorithms.dqn.DQNConfig

nnabla_rl.algorithms.dqn.DQN

GAIL

nnabla_rl.algorithms.gail.GAILConfig

nnabla_rl.algorithms.gail.GAIL

IQN

nnabla_rl.algorithms.iqn.IQNConfig

nnabla_rl.algorithms.iqn.IQN

Munchausen DQN

nnabla_rl.algorithms.munchausen_dqn.MunchausenDQNConfig

nnabla_rl.algorithms.munchausen_dqn.MunchausenDQN

Munchausen IQN

nnabla_rl.algorithms.munchausen_iqn.MunchausenIQNConfig

nnabla_rl.algorithms.munchausen_iqn.MunchausenIQN

PPO

nnabla_rl.algorithms.ppo.PPOConfig

nnabla_rl.algorithms.ppo.PPO

QRDQN

nnabla_rl.algorithms.qrdqn.QRDQNConfig

nnabla_rl.algorithms.qrdqn.QRDQN

REINFORCE

nnabla_rl.algorithms.reinforce.REINFORCEConfig

nnabla_rl.algorithms.reinforce.REINFORCE

SAC

nnabla_rl.algorithms.sac.SACConfig

nnabla_rl.algorithms.sac.SAC

SAC (ICML 2018 version)

nnabla_rl.algorithms.icml2018_sac.ICML2018SACConfig

nnabla_rl.algorithms.icml2018_sac.ICML2018SAC

TD3

nnabla_rl.algorithms.td3.TD3Config

nnabla_rl.algorithms.td3.TD3

TRPO

nnabla_rl.algorithms.trpo.TRPOConfig

nnabla_rl.algorithms.trpo.TRPO

TRPO (ICML 2015 version)

nnabla_rl.algorithms.icml2015_trpo.ICML2015TRPOConfig

nnabla_rl.algorithms.icml2015_trpo.ICML2015TRPO