MCPcopy Create free account

hub / github.com/ashedwards/ILPO / functions

Functions144 in github.com/ashedwards/ILPO

⨍ Functions 144◇ Types & classes 15
↓ 51 callersMethodrun
Runs training method.
models/bc.py:78
↓ 37 callersFunctionlrelu
(x, a)
models/utils.py:89
↓ 31 callersFunctionfully_connected
(inputs, n_outputs, reuse=False, scope=None)
models/utils.py:78
↓ 15 callersMethodprocess_inputs
Processes the inputs used for the BC policy.
models/bc.py:27
↓ 12 callersMethodcreate_model
Initializes BC model and losses.
models/bc.py:50
↓ 9 callersFunctiondeprocess
(image)
models/utils.py:107
↓ 8 callersFunctionconv
(batch_input, out_channels, stride)
models/utils.py:113
↓ 8 callersFunctionpreprocess
(image)
models/utils.py:101
↓ 6 callersFunctiondeconv
(batch_input, out_channels)
models/utils.py:125
↓ 4 callersMethodcreate_encoder
Creates an encoding of the state.
models/bc.py:12
↓ 2 callersMethodP
Returns the next_state probabilities for a state.
models/image_policy.py:130
↓ 2 callersMethodcreate_encoder
Creates an encoding of the state.
models/bco.py:12
↓ 2 callersMethodcreate_encoder
Creates an encoding of the state.
models/ilpo.py:12
↓ 2 callersMethodencode
Runs an encoding on a state.
models/bco.py:32
↓ 2 callersFunctiongetdata
(name)
results/plot_cartpole.py:13
↓ 2 callersFunctiongetdata
(name)
results/plot_acrobot.py:13
↓ 2 callersMethodgreedy
Returns the greedy remapped action for a state.
models/image_policy.py:135
↓ 2 callersMethodgreedy
Returns the greedy remapped action for a state.
models/image_policy_bco.py:133
↓ 2 callersMethodgreedy
Returns the greedy remapped action for a state.
models/vector_policy.py:112
↓ 2 callersMethodgreedy
Returns the greedy remapped action for a state.
models/vector_policy_bco.py:77
↓ 2 callersMethodrender
(self, obs)
models/image_policy.py:150
↓ 1 callersMethodP
Returns the next_state probabilities for a state.
models/vector_policy.py:107
↓ 1 callersMethodP
Returns the next_state probabilities for a state.
models/vector_policy_bc.py:32
↓ 1 callersMethodP
Returns the next_state probabilities for a state.
models/image_policy_bc.py:32
↓ 1 callersMethodaction_remap_net
Network for remapping incorrect action labels.
models/image_policy.py:113
↓ 1 callersMethodaction_remap_net
Network for remapping incorrect action labels.
models/vector_policy.py:91
↓ 1 callersFunctionbias_variable
(shape)
models/utils.py:73
↓ 1 callersFunctionbias_variable
(shape)
models/coin_utils.py:69
↓ 1 callersMethodcreate_bc
Creates the Behavioral Cloning Network.
models/bco.py:39
↓ 1 callersMethodcreate_bc
Creates the Behavioral Cloning Network.
models/bc.py:32
↓ 1 callersMethodcreate_generator
Creates a generator for making next state predictions.
models/ilpo.py:17
↓ 1 callersMethodcreate_ilpo
Creates ILPO network.
models/ilpo.py:39
↓ 1 callersMethodcreate_small_encoder
Creates state embedding.
models/image_policy_bco.py:97
↓ 1 callersMethodeval_policy
Evaluate the policy.
models/image_policy.py:154
↓ 1 callersMethodeval_policy
Evaluate the policy.
models/image_policy_bco.py:144
↓ 1 callersMethodeval_policy
Evaluate the policy.
models/vector_policy.py:124
↓ 1 callersMethodeval_policy
Evaluate the policy.
models/vector_policy_bco.py:88
↓ 1 callersMethodeval_policy
Evaluate the policy.
models/vector_policy_bc.py:47
↓ 1 callersMethodeval_policy
Evaluate the policy.
models/image_policy_bc.py:47
↓ 1 callersFunctiongetdata
(name)
results/plot_results.py:10
↓ 1 callersMethodgreedy
Returns the greedy remapped action for a state.
models/vector_policy_bc.py:37
↓ 1 callersMethodgreedy
Returns the greedy remapped action for a state.
models/image_policy_bc.py:37
↓ 1 callersMethodinverse_action
Find the minimum action for training.
models/image_policy_bco.py:92
↓ 1 callersMethodinverse_action
Find the minimum action for training.
models/vector_policy_bco.py:59
↓ 1 callersMethodload_examples
Loads in training examples.
models/bco.py:7
↓ 1 callersMethodload_examples
Loads in training examples.
models/bc.py:7
↓ 1 callersMethodload_examples
Loads in training examples.
models/ilpo.py:7
↓ 1 callersFunctionmain
()
train_expert/enjoy_acrobot.py:15
↓ 1 callersFunctionmain
()
train_expert/enjoy_cartpole.py:16
↓ 1 callersFunctionmain
()
train_expert/train_cartpole.py:12
↓ 1 callersFunctionmain
()
train_expert/train_acrobot.py:6
↓ 1 callersFunctionmain
()
models/vector_bco.py:205
↓ 1 callersFunctionmain
()
models/vector_ilpo.py:209
↓ 1 callersFunctionmain
()
models/vector_bc.py:207
↓ 1 callersFunctionmain
()
models/image_ilpo.py:318
↓ 1 callersFunctionmain
()
models/image_bco.py:318
↓ 1 callersFunctionmain
()
models/image_bc.py:257
↓ 1 callersMethodmin_action
Find the minimum action for training.
models/image_policy.py:85
↓ 1 callersMethodmin_action
Find the minimum action for training.
models/vector_policy.py:61
↓ 1 callersMethodpolicy_net
Network for remapping incorrect action labels.
models/image_policy_bco.py:120
↓ 1 callersMethodpolicy_net
Network for remapping incorrect action labels.
models/vector_policy_bco.py:64
↓ 1 callersFunctionprocess_obs
(image_file)
models/image_policy_bco.py:43
↓ 1 callersMethodrender
(self, obs)
models/image_policy_bco.py:175
↓ 1 callersMethodrun_policy
Run the policy.
models/image_policy.py:189
↓ 1 callersMethodrun_policy
Run the policy.
models/image_policy_bco.py:180
↓ 1 callersMethodrun_policy
Run the policy.
models/vector_policy.py:141
↓ 1 callersMethodrun_policy
Run the policy.
models/vector_policy_bco.py:105
↓ 1 callersMethodrun_policy
Run the policy.
models/vector_policy_bc.py:63
↓ 1 callersMethodrun_policy
Run the policy.
models/image_policy_bc.py:63
↓ 1 callersMethodtrain_examples
Trains the model. TODO: Place method here.
models/bco.py:22
↓ 1 callersMethodtrain_examples
Trains the model. TODO: Place method here.
models/bc.py:22
↓ 1 callersMethodtrain_examples
Trains the model. TODO: Place method here.
models/ilpo.py:22
↓ 1 callersFunctionweight_variable
(shape)
models/utils.py:68
↓ 1 callersFunctionweight_variable
(shape)
models/coin_utils.py:64
Method__init__
Initializes the ILPO policy network.
models/image_policy.py:36
Method__init__
Initializes the ILPO policy network.
models/image_policy_bco.py:57
Method__init__
Initializes the ILPO policy network.
models/vector_policy.py:13
Method__init__
Initializes the ILPO policy network.
models/vector_policy_bco.py:24
Method__init__
Initializes the BC network.
models/vector_policy_bc.py:11
Method__init__
Initializes the BC network.
models/image_policy_bc.py:14
Functioncallback
(lcl, _glb)
train_expert/train_cartpole.py:6
Functioncheck_image
(image)
models/utils.py:138
Functioncheck_image
(image)
models/coin_utils.py:134
Functionconv
(batch_input, out_channels, stride)
models/coin_utils.py:109
Methodconvert
(image)
models/image_ilpo.py:179
Methodconvert
(image)
models/image_bco.py:180
Methodcreate_encoder
Creates state embedding.
models/vector_bco.py:75
Methodcreate_encoder
Creates state embedding.
models/vector_ilpo.py:75
Methodcreate_encoder
Creates state embedding.
models/vector_bc.py:70
Methodcreate_encoder
Creates state embedding.
models/image_ilpo.py:100
Methodcreate_encoder
Creates state embedding.
models/image_bco.py:101
Methodcreate_encoder
Creates state embedding.
models/image_bc.py:91
Methodcreate_generator
Returns next state prediction given state and latent action.
models/vector_bco.py:97
Methodcreate_generator
Returns next state prediction given state and latent action.
models/vector_ilpo.py:97
Methodcreate_generator
(self, layers, generator_outputs_channels)
models/vector_bc.py:92
Methodcreate_generator
Returns next state prediction given a combined state and latent action.
models/image_ilpo.py:128
Methodcreate_generator
Creates a generator for making next state predictions.
models/bco.py:17
Methodcreate_generator
Creates a generator for making next state predictions.
models/bc.py:17
Methodcreate_generator
Returns next state prediction given a combined state and latent action.
models/image_bco.py:129
Methodcreate_generator
(self, layers, generator_outputs_channels)
models/image_bc.py:118
next →1–100 of 144, ranked by callers