MCPcopy Create free account

hub / github.com/brendanator/atari-rl / functions

Functions138 in github.com/brendanator/atari-rl

⨍ Functions 138◇ Types & classes 25
Method__init__
(self, name, inputs, conv_outputs, reward_scaling, config)
networks/dqn.py:183
Method__init__
(self, summary, config)
atari/atari.py:10
Method__init__
(self, **kwargs)
test/mock.py:2
Method__init__
(self, config)
agents/exploration_bonus.py:10
Method__init__
(self, config)
agents/replay_memory.py:12
Method__init__
(self, replay_memory, required_feeds, indices)
agents/replay_memory.py:159
Method__init__
(self, policy_network, replay_memory, summary, config)
agents/agent.py:8
Method__init__
(self)
agents/replay_priorities.py:7
Method__init__
(self, config)
agents/replay_priorities.py:29
Method__init__
(self, config)
agents/training.py:10
Method__init__
(self, config)
util/summary.py:5
Method__missing__
(self, key)
util/util.py:106
Method__str__
(self)
agents/replay_priorities.py:95
Method_get_image
(self)
atari/atari.py:108
Functionadd_loss_summaries
Add summaries for losses in model. Generates moving average for all losses and associated summaries for visualizing the performance of the networ
util/util.py:51
Methodbatch_sigma_squared
(self, batch)
networks/reward_scaling.py:23
Methodchoose_action
(self)
networks/dqn.py:134
Methodepsilon
(self, step, epsilon)
util/summary.py:12
Functionformat_offset
(prefix, t)
util/util.py:42
Methodlog_episode
(self, step)
atari/atari.py:84
Functionmain
(_)
main.py:120
Functionmemoize
Memoization decorator for a function taking one or more arguments. Taken from here: https://goo.gl/gxOVPQ
util/util.py:97
Functionoffset_data
(t, name)
networks/inputs.py:65
Methodprobabilities
(self, indices)
agents/replay_priorities.py:80
Methodright_child
(self, index)
agents/replay_priorities.py:92
Functionrun_directory
(config)
util/util.py:11
Methodsample_indices
(self, count)
agents/replay_priorities.py:16
Functionscale_gradient
(inputs, scale)
util/util.py:78
Methodscale_gradients
(self, grads, variables_to_scale)
networks/reward_scaling.py:70
Functionscaled_gradient
(op, grad)
util/util.py:84
Functionstop_training
(signum, frame)
main.py:125
Methodtest_proportional_priority
(self)
test/test_replay_priorities.py:10
Methodtest_replay_memory
(self)
test/test_replay_memory.py:10
Methodunnormalize_output
(self, output)
networks/reward_scaling.py:63
Methodupdate_priorities
(self, indices, priorities)
agents/replay_priorities.py:13
Methodvariables
(self)
networks/reward_scaling.py:43
Methodvariables
(self)
networks/reward_scaling.py:67
Methodvariables
(self)
networks/dqn.py:141
← previous101–138 of 138, ranked by callers