MCPcopy Create free account

hub / github.com/Ericonaldo/ILSwiss / functions

Functions830 in github.com/Ericonaldo/ILSwiss

Methoddenormalize
(self, v)
rlkit/torch/utils/normalizer.py:70
Methoddenormalize
(self, v)
rlkit/data_management/normalizer.py:48
Methoddenormalize
(self, v)
rlkit/data_management/normalizer.py:77
Methoddenormalize
(self, v)
rlkit/data_management/normalizer.py:116
Methoddenormalize_scale
Only denormalize the scale. Do not add the mean.
rlkit/torch/utils/normalizer.py:78
Functiondump_tabular
(*args, **kwargs)
rlkit/core/logger.py:300
Methodend_epoch
(self)
rlkit/torch/algorithms/sac/sac_ae.py:419
Methodend_epoch
(self)
rlkit/torch/algorithms/sac/sac.py:272
Methodend_epoch
(self)
rlkit/torch/algorithms/sac/sac_alpha.py:278
Methodend_epoch
(self)
rlkit/torch/algorithms/her/td3.py:244
Methodend_epoch
(self)
rlkit/torch/algorithms/her/sac.py:246
Methodend_epoch
(self)
rlkit/torch/algorithms/gcsl/gcsl.py:111
Methodend_epoch
(self)
rlkit/torch/algorithms/ppo/ppo.py:201
Methodend_epoch
(self)
rlkit/torch/algorithms/discrete_sac/discrete_sac.py:212
Methodend_epoch
(self)
rlkit/core/trainer.py:22
Methodenvs
(self)
rlkit/envs/envpool.py:14
Methodestimate_obs_stats
(self, obs_batch, override_values=False)
rlkit/envs/wrappers.py:312
Functioneval_np
Eval this module with a numpy interface Same as a call to __call__ except all Variable input/outputs are replaced with numpy equivalents
rlkit/torch/core.py:92
Methodevaluate
(self, epoch)
rlkit/torch/algorithms/torch_rl_algorithm.py:55
Methodevaluate
(self, epoch, *args, **kwargs)
rlkit/torch/algorithms/torch_base_algorithm.py:26
Methodevaluate
(self, epoch: int)
rlkit/torch/algorithms/mbpo/mbpo.py:165
Methodevaluate
Evaluate the policy, e.g. save/print progress. :param epoch: :return:
rlkit/torch/algorithms/bc/bc.py:112
Methodevaluate
(self, epoch)
rlkit/torch/algorithms/adv_irl/adv_irl.py:120
Methodexpand
(v)
rlkit/torch/common/distributions.py:32
Functionextract_demo_dict
(demo_file)
rlkit/data_management/mil_utils.py:73
Functionf
(step)
rlkit/core/train_util.py:6
Functionfanin_init
(tensor)
rlkit/torch/utils/pytorch_util.py:20
Functionfanin_init_weights_like
(tensor)
rlkit/torch/utils/pytorch_util.py:32
Methodfind_batch
Return a batch of size `batch_size`. Find batch which ends with (s,a) in target_batch :param batch_size: :return:
rlkit/data_management/episodic_replay_buffer.py:154
Methodforward
(self, inputs)
rlkit/torch/utils/transform_layer.py:214
Methodforward
(self, obs, detach=False)
rlkit/torch/common/encoders.py:88
Methodforward
(self, obs, detach=False)
rlkit/torch/common/encoders.py:122
Methodforward
(self, h)
rlkit/torch/common/encoders.py:163
Methodforward
(self, obs, deterministic=False)
rlkit/torch/common/policies.py:166
Methodforward
:param obs: Observation :param deterministic: If True, do not sample :param return_log_prob: If True, return a sample and its
rlkit/torch/common/policies.py:248
Methodforward
:param obs: Observation :param deterministic: If True, do not sample :param return_log_prob: If True, return a sample and its
rlkit/torch/common/policies.py:388
Methodforward
(self, obs, deterministic=False)
rlkit/torch/common/policies.py:533
Methodforward
:param obs: Observation
rlkit/torch/common/policies.py:749
Methodforward
(self, x, x_hat)
rlkit/torch/common/modules.py:14
Methodforward
(self, x)
rlkit/torch/common/modules.py:38
Methodforward
(self, *inputs, **kwargs)
rlkit/torch/common/networks.py:113
Methodforward
(self, input, return_preactivations=False)
rlkit/torch/common/networks.py:128
Methodforward
(self, input: torch.Tensor)
rlkit/torch/common/networks.py:162
Methodforward
(self, batch)
rlkit/torch/algorithms/adv_irl/disc_models/rnn_disc_models.py:71
Methodforward
(self, batch)
rlkit/torch/algorithms/adv_irl/disc_models/simple_disc_models.py:43
Methodforward
(self, batch)
rlkit/torch/algorithms/adv_irl/disc_models/simple_disc_models.py:85
Methodforward
(self, obs, vec=None)
rlkit/torch/algorithms/adv_irl/disc_models/cnn_disc_models.py:64
Functionfrom_numpy
(np_array, requires_grad=False)
rlkit/torch/utils/pytorch_util.py:84
Functiongenerate_gif
(list_of_img_list, names, save_path)
rlkit/core/vistools.py:70
Functiongenerate_noise
Generate a T x dU gaussian-distributed noise vector. This will approximately have mean 0 and variance 1, ignoring smoothing. Args:
rlkit/data_management/mil_utils.py:112
Methodget_action
(self, observation)
rlkit/torch/common/policies.py:23
Methodget_action
(self, obs_np, deterministic=False)
rlkit/torch/common/policies.py:60
Methodget_action
deterministic=False makes no diff, just doing this for consistency in interface for now
rlkit/torch/common/policies.py:154
Methodget_action
(self, obs_np, deterministic=False)
rlkit/torch/common/policies.py:241
Methodget_action
(self, obs_np, deterministic=False)
rlkit/torch/common/policies.py:381
Methodget_action
deterministic=False makes no diff, just doing this for consistency in interface for now
rlkit/torch/common/policies.py:522
Methodget_action
deterministic=False makes no diff, just doing this for consistency in interface for now
rlkit/torch/common/policies.py:587
Methodget_action
deterministic=False makes no diff, just doing this for consistency in interface for now
rlkit/torch/common/policies.py:778
Methodget_action
(self, obs)
rlkit/policies/simple.py:12
Methodget_action
(self, obs)
rlkit/policies/argmax.py:16
Methodget_action
(self, t, policy, *args, **kwargs)
rlkit/exploration_strategies/base.py:27
Methodget_action
(self, *args, **kwargs)
rlkit/exploration_strategies/base.py:52
Methodget_action_from_raw_action
(self, action, t=0, **kwargs)
rlkit/exploration_strategies/ou_strategy.py:55
Methodget_action_from_raw_action
(self, action, t=None, **kwargs)
rlkit/exploration_strategies/gaussian_strategy.py:25
Methodget_action_from_raw_action
(self, action, **kwargs)
rlkit/exploration_strategies/epsilon_greedy.py:21
Methodget_actions
(self, observations)
rlkit/torch/common/policies.py:26
Methodget_actions
(self, t, observation, policy, **kwargs)
rlkit/exploration_strategies/base.py:31
Methodget_actions
(self, *args, **kwargs)
rlkit/exploration_strategies/base.py:55
Methodget_actions_from_raw_actions
(self, actions, t=0, **kwargs)
rlkit/exploration_strategies/ou_strategy.py:62
Methodget_all
(self, keys=None, **kwargs)
rlkit/data_management/aug_replay_buffer.py:165
Methodget_all
(self, keys=None, relabel=True, **kwargs)
rlkit/data_management/relabel_horizon_replay_buffer.py:35
Methodget_all_stacked
(self)
rlkit/data_management/path_builder.py:46
Functionget_average_returns
(paths, std=False)
rlkit/core/eval_util.py:83
Methodget_batch
(self, keys=None)
rlkit/torch/algorithms/her/her.py:27
Methodget_batch
(self, keys=None)
rlkit/torch/algorithms/gcsl/rl.py:40
Methodget_epoch_snapshot
(self, epoch)
rlkit/torch/algorithms/torch_rl_algorithm.py:42
Methodget_epoch_snapshot
(self, epoch)
rlkit/torch/algorithms/ddpg/ddpg.py:237
Methodget_epoch_snapshot
(self, epoch)
rlkit/torch/algorithms/dqn/dqn.py:238
Methodget_epoch_snapshot
(self, epoch)
rlkit/torch/algorithms/adv_irl/adv_irl.py:320
Methodget_epoch_snapshot
(self, epoch)
rlkit/torch/algorithms/dagger/dagger.py:79
Methodget_eval_statistics
(self)
rlkit/torch/algorithms/sac/sac_ae.py:416
Methodget_eval_statistics
(self)
rlkit/torch/algorithms/sac/sac.py:269
Methodget_eval_statistics
(self)
rlkit/torch/algorithms/sac/sac_alpha.py:275
Methodget_eval_statistics
(self)
rlkit/torch/algorithms/her/td3.py:241
Methodget_eval_statistics
(self)
rlkit/torch/algorithms/her/sac.py:243
Methodget_eval_statistics
(self)
rlkit/torch/algorithms/gcsl/gcsl.py:108
Methodget_eval_statistics
(self)
rlkit/torch/algorithms/ppo/ppo.py:198
Methodget_eval_statistics
(self)
rlkit/torch/algorithms/discrete_sac/discrete_sac.py:209
Methodget_eval_statistics
(self)
rlkit/core/trainer.py:16
Functionget_generic_path_information
Get an OrderedDict with a bunch of statistic names and values.
rlkit/core/eval_util.py:15
Methodget_initial_pairs
Return a list of initial pairs of each traj.
rlkit/data_management/episodic_replay_buffer.py:101
Methodget_last_pairs
Return a list of initial pairs of each traj.
rlkit/data_management/episodic_replay_buffer.py:110
Methodget_log_prob
(self, obs, acts, return_normal_params=False)
rlkit/torch/common/policies.py:329
Methodget_log_prob
(self, obs, acts, return_normal_params=False)
rlkit/torch/common/policies.py:461
Methodget_log_prob_entropy
(self, obs, acts)
rlkit/torch/common/policies.py:309
Functionget_log_tabular_only
()
rlkit/core/logger.py:188
Functionget_log_tboard
()
rlkit/core/logger.py:197
Functionget_numpy
(tensor: torch.Tensor)
rlkit/torch/utils/pytorch_util.py:91
Methodget_param_values
(self)
rlkit/policies/base.py:32
Methodget_param_values
(self)
rlkit/exploration_strategies/base.py:62
← previousnext →501–600 of 830, ranked by callers