Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/TianhongDai/reinforcement-learning-algorithms
/ functions
Functions
284 in github.com/TianhongDai/reinforcement-learning-algorithms
⨍
Functions
284
◇
Types & classes
57
Method
close
(self)
rl_utils/logger/logger.py:135
Method
close
(self)
rl_utils/logger/logger.py:169
Method
close
(self)
rl_utils/logger/bench.py:79
Method
close_extras
(self)
rl_utils/env_wrapper/multi_envs_wrapper.py:83
Method
count
(self)
rl_utils/env_wrapper/atari_wrapper.py:262
Function
decorator_with_name
(func)
rl_utils/logger/logger.py:277
Function
error
(*args)
rl_utils/logger/logger.py:239
Method
forward
(self, obs, action=None)
rl_algorithms/sac/models.py:14
Method
forward
(self, obs)
rl_algorithms/sac/models.py:34
Method
forward
(self, x)
rl_algorithms/ddpg/models.py:13
Method
forward
(self, x, actions)
rl_algorithms/ddpg/models.py:26
Method
forward
(self, x)
rl_algorithms/a2c/models.py:24
Method
forward
(self, inputs)
rl_algorithms/a2c/models.py:46
Method
forward
(self, x)
rl_algorithms/ppo/models.py:38
Method
forward
(self, x)
rl_algorithms/ppo/models.py:76
Method
forward
(self, inputs)
rl_algorithms/ppo/models.py:98
Method
forward
(self, x)
rl_algorithms/dqn_algos/models.py:22
Method
forward
(self, inputs)
rl_algorithms/dqn_algos/models.py:49
Method
forward
(self, x)
rl_algorithms/trpo/models.py:12
Method
forward
(self, x)
rl_algorithms/trpo/models.py:24
Method
forward
(self, x)
rl_algorithms/trpo/models.py:38
Method
frame
(self, i)
rl_utils/env_wrapper/atari_wrapper.py:266
Function
func_wrapper
(*args, **kwargs)
rl_utils/logger/logger.py:278
Function
get_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
Method
get_episode_lengths
(self)
rl_utils/logger/bench.py:89
Method
get_episode_rewards
(self)
rl_utils/logger/bench.py:86
Method
get_episode_times
(self)
rl_utils/logger/bench.py:92
Method
get_images
(self)
rl_utils/env_wrapper/multi_envs_wrapper.py:93
Method
get_images
(self)
rl_utils/env_wrapper/__init__.py:159
Method
get_length
(self)
rl_algorithms/dqn_algos/utils.py:44
Function
get_monitor_files
(dir)
rl_utils/logger/bench.py:122
Method
get_total_steps
(self)
rl_utils/logger/bench.py:83
Method
get_viewer
(self)
rl_utils/env_wrapper/__init__.py:124
Function
getkvs
()
rl_utils/logger/logger.py:220
Function
logkvs
Log a dictionary of key-value pairs
rl_utils/logger/logger.py:207
Method
mean
(self)
rl_utils/running_filter/running_filter.py:30
Method
n
(self)
rl_utils/running_filter/running_filter.py:26
Method
num_episodes
(self)
rl_algorithms/dqn_algos/utils.py:53
Method
observation
(self, obs)
rl_utils/env_wrapper/atari_wrapper.py:169
Method
observation
(self, observation)
rl_utils/env_wrapper/atari_wrapper.py:227
Method
output_shape
(self, input_space)
rl_utils/running_filter/running_filter.py:69
Function
profile
Usage: @profile("my_func") def my_func(): code
rl_utils/logger/logger.py:271
Function
read_csv
(fname)
rl_utils/logger/logger.py:464
Function
read_json
(fname)
rl_utils/logger/logger.py:456
Function
read_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
Method
render
(self, mode='human')
rl_utils/env_wrapper/__init__.py:156
Function
reset
()
rl_utils/logger/logger.py:405
Method
reset
Do no-op action for a number of steps in [1, noop_max].
rl_utils/env_wrapper/atari_wrapper.py:26
Method
reset
(self, **kwargs)
rl_utils/env_wrapper/atari_wrapper.py:51
Method
reset
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
Method
reset
(self, **kwargs)
rl_utils/env_wrapper/atari_wrapper.py:125
Method
reset
(self)
rl_utils/env_wrapper/atari_wrapper.py:207
Method
reset
(self)
rl_utils/env_wrapper/__init__.py:146
Method
reset
(self)
rl_utils/env_wrapper/__init__.py:172
Method
reset
(self)
rl_utils/env_wrapper/frame_stack.py:26
Method
reset
(self, **kwargs)
rl_utils/logger/bench.py:35
Method
reward
Bin reward to {+1, 0, -1} by its sign.
rl_utils/env_wrapper/atari_wrapper.py:132
Method
sample
(self, batch_size)
rl_utils/experience_replay/experience_replay.py:39
Method
sample_n
(self, n, return_pre_tanh_value=False)
rl_algorithms/sac/utils.py:18
Function
scoped_configure
(dir=None, format_strs=None, comm=None)
rl_utils/logger/logger.py:412
Function
set_comm
(comm)
rl_utils/logger/logger.py:249
Method
shape
(self)
rl_utils/running_filter/running_filter.py:42
Method
step
(self, ac)
rl_utils/env_wrapper/atari_wrapper.py:41
Method
step
(self, ac)
rl_utils/env_wrapper/atari_wrapper.py:61
Method
step
(self, action)
rl_utils/env_wrapper/atari_wrapper.py:73
Method
step
Repeat action, sum reward, and max over last observations.
rl_utils/env_wrapper/atari_wrapper.py:108
Method
step
(self, action)
rl_utils/env_wrapper/atari_wrapper.py:213
Method
step_async
(self, actions)
rl_utils/env_wrapper/multi_envs_wrapper.py:64
Method
step_async
(self, actions)
rl_utils/env_wrapper/__init__.py:142
Method
step_wait
(self)
rl_utils/env_wrapper/multi_envs_wrapper.py:70
Method
step_wait
(self)
rl_utils/env_wrapper/__init__.py:150
Method
step_wait
(self)
rl_utils/env_wrapper/__init__.py:176
Method
step_wait
(self)
rl_utils/env_wrapper/frame_stack.py:17
Method
summary_val
(k, v)
rl_utils/logger/logger.py:159
Method
unwrapped
(self)
rl_utils/env_wrapper/__init__.py:118
Method
update
(self, v)
rl_utils/mpi_utils/normalizer.py:25
Method
var
(self)
rl_utils/running_filter/running_filter.py:34
Function
warn
(*args)
rl_utils/logger/logger.py:236
Function
worker
(remote, parent_remote, env_fn_wrapper)
rl_utils/env_wrapper/multi_envs_wrapper.py:5
Method
writekvs
(self, kvs)
rl_utils/logger/logger.py:37
Method
writekvs
(self, kvs)
rl_utils/logger/logger.py:92
Method
writekvs
(self, kvs)
rl_utils/logger/logger.py:108
Method
writekvs
(self, kvs)
rl_utils/logger/logger.py:158
Method
writeseq
(self, seq)
rl_utils/logger/logger.py:75
← previous
201–284 of 284, ranked by callers