MCPcopy Create free account

hub / github.com/TianhongDai/reinforcement-learning-algorithms / functions

Functions284 in github.com/TianhongDai/reinforcement-learning-algorithms

Methodclose
(self)
rl_utils/logger/logger.py:135
Methodclose
(self)
rl_utils/logger/logger.py:169
Methodclose
(self)
rl_utils/logger/bench.py:79
Methodclose_extras
(self)
rl_utils/env_wrapper/multi_envs_wrapper.py:83
Methodcount
(self)
rl_utils/env_wrapper/atari_wrapper.py:262
Functiondecorator_with_name
(func)
rl_utils/logger/logger.py:277
Functionerror
(*args)
rl_utils/logger/logger.py:239
Methodforward
(self, obs, action=None)
rl_algorithms/sac/models.py:14
Methodforward
(self, obs)
rl_algorithms/sac/models.py:34
Methodforward
(self, x)
rl_algorithms/ddpg/models.py:13
Methodforward
(self, x, actions)
rl_algorithms/ddpg/models.py:26
Methodforward
(self, x)
rl_algorithms/a2c/models.py:24
Methodforward
(self, inputs)
rl_algorithms/a2c/models.py:46
Methodforward
(self, x)
rl_algorithms/ppo/models.py:38
Methodforward
(self, x)
rl_algorithms/ppo/models.py:76
Methodforward
(self, inputs)
rl_algorithms/ppo/models.py:98
Methodforward
(self, x)
rl_algorithms/dqn_algos/models.py:22
Methodforward
(self, inputs)
rl_algorithms/dqn_algos/models.py:49
Methodforward
(self, x)
rl_algorithms/trpo/models.py:12
Methodforward
(self, x)
rl_algorithms/trpo/models.py:24
Methodforward
(self, x)
rl_algorithms/trpo/models.py:38
Methodframe
(self, i)
rl_utils/env_wrapper/atari_wrapper.py:266
Functionfunc_wrapper
(*args, **kwargs)
rl_utils/logger/logger.py:278
Functionget_dir
Get directory that log files are being written to. will be None if there is no output directory (i.e., if you didn't call start)
rl_utils/logger/logger.py:252
Methodget_episode_lengths
(self)
rl_utils/logger/bench.py:89
Methodget_episode_rewards
(self)
rl_utils/logger/bench.py:86
Methodget_episode_times
(self)
rl_utils/logger/bench.py:92
Methodget_images
(self)
rl_utils/env_wrapper/multi_envs_wrapper.py:93
Methodget_images
(self)
rl_utils/env_wrapper/__init__.py:159
Methodget_length
(self)
rl_algorithms/dqn_algos/utils.py:44
Functionget_monitor_files
(dir)
rl_utils/logger/bench.py:122
Methodget_total_steps
(self)
rl_utils/logger/bench.py:83
Methodget_viewer
(self)
rl_utils/env_wrapper/__init__.py:124
Functiongetkvs
()
rl_utils/logger/logger.py:220
Functionlogkvs
Log a dictionary of key-value pairs
rl_utils/logger/logger.py:207
Methodmean
(self)
rl_utils/running_filter/running_filter.py:30
Methodn
(self)
rl_utils/running_filter/running_filter.py:26
Methodnum_episodes
(self)
rl_algorithms/dqn_algos/utils.py:53
Methodobservation
(self, obs)
rl_utils/env_wrapper/atari_wrapper.py:169
Methodobservation
(self, observation)
rl_utils/env_wrapper/atari_wrapper.py:227
Methodoutput_shape
(self, input_space)
rl_utils/running_filter/running_filter.py:69
Functionprofile
Usage: @profile("my_func") def my_func(): code
rl_utils/logger/logger.py:271
Functionread_csv
(fname)
rl_utils/logger/logger.py:464
Functionread_json
(fname)
rl_utils/logger/logger.py:456
Functionread_tb
path : a tensorboard file OR a directory, where we will find all TB files of the form events.*
rl_utils/logger/logger.py:468
Methodrender
(self, mode='human')
rl_utils/env_wrapper/__init__.py:156
Functionreset
()
rl_utils/logger/logger.py:405
Methodreset
Do no-op action for a number of steps in [1, noop_max].
rl_utils/env_wrapper/atari_wrapper.py:26
Methodreset
(self, **kwargs)
rl_utils/env_wrapper/atari_wrapper.py:51
Methodreset
Reset only when lives are exhausted. This way all states are still reachable even though lives are episodic, and the learner need not
rl_utils/env_wrapper/atari_wrapper.py:87
Methodreset
(self, **kwargs)
rl_utils/env_wrapper/atari_wrapper.py:125
Methodreset
(self)
rl_utils/env_wrapper/atari_wrapper.py:207
Methodreset
(self)
rl_utils/env_wrapper/__init__.py:146
Methodreset
(self)
rl_utils/env_wrapper/__init__.py:172
Methodreset
(self)
rl_utils/env_wrapper/frame_stack.py:26
Methodreset
(self, **kwargs)
rl_utils/logger/bench.py:35
Methodreward
Bin reward to {+1, 0, -1} by its sign.
rl_utils/env_wrapper/atari_wrapper.py:132
Methodsample
(self, batch_size)
rl_utils/experience_replay/experience_replay.py:39
Methodsample_n
(self, n, return_pre_tanh_value=False)
rl_algorithms/sac/utils.py:18
Functionscoped_configure
(dir=None, format_strs=None, comm=None)
rl_utils/logger/logger.py:412
Functionset_comm
(comm)
rl_utils/logger/logger.py:249
Methodshape
(self)
rl_utils/running_filter/running_filter.py:42
Methodstep
(self, ac)
rl_utils/env_wrapper/atari_wrapper.py:41
Methodstep
(self, ac)
rl_utils/env_wrapper/atari_wrapper.py:61
Methodstep
(self, action)
rl_utils/env_wrapper/atari_wrapper.py:73
Methodstep
Repeat action, sum reward, and max over last observations.
rl_utils/env_wrapper/atari_wrapper.py:108
Methodstep
(self, action)
rl_utils/env_wrapper/atari_wrapper.py:213
Methodstep_async
(self, actions)
rl_utils/env_wrapper/multi_envs_wrapper.py:64
Methodstep_async
(self, actions)
rl_utils/env_wrapper/__init__.py:142
Methodstep_wait
(self)
rl_utils/env_wrapper/multi_envs_wrapper.py:70
Methodstep_wait
(self)
rl_utils/env_wrapper/__init__.py:150
Methodstep_wait
(self)
rl_utils/env_wrapper/__init__.py:176
Methodstep_wait
(self)
rl_utils/env_wrapper/frame_stack.py:17
Methodsummary_val
(k, v)
rl_utils/logger/logger.py:159
Methodunwrapped
(self)
rl_utils/env_wrapper/__init__.py:118
Methodupdate
(self, v)
rl_utils/mpi_utils/normalizer.py:25
Methodvar
(self)
rl_utils/running_filter/running_filter.py:34
Functionwarn
(*args)
rl_utils/logger/logger.py:236
Functionworker
(remote, parent_remote, env_fn_wrapper)
rl_utils/env_wrapper/multi_envs_wrapper.py:5
Methodwritekvs
(self, kvs)
rl_utils/logger/logger.py:37
Methodwritekvs
(self, kvs)
rl_utils/logger/logger.py:92
Methodwritekvs
(self, kvs)
rl_utils/logger/logger.py:108
Methodwritekvs
(self, kvs)
rl_utils/logger/logger.py:158
Methodwriteseq
(self, seq)
rl_utils/logger/logger.py:75
← previous201–284 of 284, ranked by callers