MCPcopy Create free account

hub / github.com/Ericonaldo/ILSwiss / functions

Functions830 in github.com/Ericonaldo/ILSwiss

Functionplot_seaborn_heatmap
(x, y, num_bins, title, save_path, ax_lims=None)
rlkit/core/vistools.py:32
Methodpredict
( self, input: torch.Tensor, factored: bool = False )
rlkit/torch/common/networks.py:265
Functionprefix
(key)
rlkit/core/logger.py:261
Methodpretrain
(self)
rlkit/torch/algorithms/ddpg/ddpg.py:257
Functionprint_color
Prints text in the specified colors Color codes: red, blue, green, white, black, yellow, magenta, cyan, reset :param te
rlkit/data_management/mil_color_print.py:147
Functionprint_grad_hook
(grad)
rlkit/torch/utils/pytorch_util.py:150
Functionquery_yes_no
Ask a yes/no question via raw_input() and return their answer. "question" is a string that is presented to the user. "default" is the presume
rlkit/launchers/launcher_util.py:357
Functionrand
(*args, torch_device=None, **kwargs)
rlkit/torch/utils/pytorch_util.py:119
Functionrandn
(*args, torch_device=None, **kwargs)
rlkit/torch/utils/pytorch_util.py:113
Methodrandom_batch
(self, batch_size, keys=None, paths=None, **kwargs)
rlkit/data_management/aug_replay_buffer.py:142
Methodrandom_batch
( self, batch_size, keys=None, multi_step=False, step_num=1, **kwargs )
rlkit/data_management/simple_replay_buffer.py:239
Methodrandom_batch
(self, batch_size, keys=None, **kwargs)
rlkit/data_management/relabel_replay_buffer.py:64
Methodrandom_batch
Return a batch of size `batch_size`. :param batch_size: :return:
rlkit/data_management/episodic_replay_buffer.py:145
Methodrandom_batch
(self, batch_size, keys=None, relabel=True, **kwargs)
rlkit/data_management/relabel_horizon_replay_buffer.py:139
Functionrandom_translate
(imgs, size, return_random_idxs=False, h1s=None, w1s=None)
rlkit/data_management/data_augmentation.py:296
Functionrecord_tabular_misc_stat
(key, values, placement="back")
rlkit/core/logger.py:385
Functionrecursive_items
Get all (key, item) recursively in a potentially recursive dictionary. Usage: ``` x = { 'foo' : { 'bar' : 5
rlkit/launchers/launcher_util.py:24
Functionremove_tabular_output
(file_name)
rlkit/core/logger.py:122
Functionremove_text_output
(file_name)
rlkit/core/logger.py:114
Methodrender
Render all of the environments.
rlkit/envs/vecenvs.py:279
Methodrender
Render the environment.
rlkit/envs/worker/base.py:54
Methodrender
(self, **kwargs: Any)
rlkit/envs/worker/dummy.py:35
Methodreparameterize
(self, mu, logstd)
rlkit/torch/common/encoders.py:68
Methodreset
(self)
rlkit/exploration_strategies/base.py:35
Methodreset
(self)
rlkit/exploration_strategies/base.py:58
Methodreset
Reset the state of some envs and return initial observations. If id is None, reset the state of all the environments and return initia
rlkit/envs/vecenvs.py:158
Methodreset
(self, **kwargs)
rlkit/envs/wrappers.py:120
Methodreset
(self, **kwargs)
rlkit/envs/wrappers.py:183
Methodreset
(self, **kwargs)
rlkit/envs/wrappers.py:249
Methodreset
(self)
rlkit/envs/wrappers.py:383
Methodreset
(self)
rlkit/envs/worker/base.py:21
Methodreset
(self)
rlkit/envs/worker/dummy.py:18
Methodreset_model
(self)
rlkit/envs/mujoco/ant.py:37
Methodreset_model
(self)
rlkit/envs/mujoco/humanoid.py:62
Methodreset_model
(self)
rlkit/envs/mujoco/walker2d.py:29
Methodreset_model
(self)
rlkit/envs/mujoco/hopper.py:32
Functionrgb2hsv
(rgb, eps=1e-8)
rlkit/torch/utils/transform_layer.py:8
Functionrun_experiment_here
Run an experiment locally without any serialization. :param experiment_function: Function. `variant` will be passed in as its only argum
rlkit/launchers/launcher_util.py:104
Methodsample_n
(self, n, return_pre_tanh_value=False)
rlkit/torch/common/distributions.py:67
Methodsample_trajs
(self, num_trajs, keys=None, samples_per_traj=None)
rlkit/data_management/simple_replay_buffer.py:349
Methodsave_data
(self, save_name)
rlkit/data_management/simple_replay_buffer.py:110
Methodsave_data
(self, save_name)
rlkit/data_management/relabel_replay_buffer.py:146
Methodsave_data
(self, save_name)
rlkit/data_management/relabel_horizon_replay_buffer.py:244
Functionsave_extra_data
Data saved here will always override the last entry :param data: Something pickle'able.
rlkit/core/logger.py:242
Functionsave_itr_params
(itr, params)
rlkit/core/logger.py:345
Functionsave_pytorch_tensor_as_img
(tensor, save_path)
rlkit/core/vistools.py:61
Methodseed
Set the seed for all environments. Accept ``None``, an int (which will extend ``i`` to ``[i, i + 1, i + 2, ...]``) or a list.
rlkit/envs/vecenvs.py:259
Methodseed
(self, seed: Optional[int] = None)
rlkit/envs/worker/base.py:50
Methodseed
(self, seed: Optional[int] = None)
rlkit/envs/worker/dummy.py:31
Methodsend_action
(self, action: np.ndarray)
rlkit/envs/worker/subproc.py:188
Methodsend_action
(self, action: np.ndarray)
rlkit/envs/worker/dummy.py:28
Methodset_data
Set the buffer with a list-like data.
rlkit/data_management/episodic_replay_buffer.py:69
Functionset_device
(gpu_id)
rlkit/torch/utils/pytorch_util.py:73
Functionset_log_tabular_only
(log_tabular_only)
rlkit/core/logger.py:183
Functionset_log_tboard
(log_tboard)
rlkit/core/logger.py:192
Methodset_num_steps_total
(self, t)
rlkit/torch/common/policies.py:519
Methodset_num_steps_total
(self, t)
rlkit/exploration_strategies/base.py:49
Methodset_param_values
(self, values)
rlkit/policies/base.py:35
Methodset_param_values
(self, param_values)
rlkit/exploration_strategies/base.py:65
Methodset_param_values_np
(self, param_values)
rlkit/torch/core.py:26
Methodset_param_values_np
(self, values)
rlkit/policies/base.py:45
Methodset_param_values_np
(self, param_values)
rlkit/exploration_strategies/base.py:71
Functionset_snapshot_dir
(dir_name, variant, log_tboard=True, log_wandb=True)
rlkit/core/logger.py:143
Functionset_snapshot_gap
(gap)
rlkit/core/logger.py:178
Functionset_snapshot_mode
(mode)
rlkit/core/logger.py:169
Functionset_title
(title)
rlkit/data_management/mil_color_print.py:28
Functionsimple_separated_format
Construct a simple TableFormat with columns separated by a separator. >>> tsv = simple_separated_format("\\t") ; \ tabulate([["foo", 1],
rlkit/core/tabulate.py:237
Functionsoft_update_from_to
(source, target, tau)
rlkit/torch/utils/pytorch_util.py:10
Functionstack_list
(lst)
rlkit/data_management/path_builder.py:63
Methodstart_training
(self, start_epoch: int = 0)
rlkit/torch/algorithms/mbpo/mbpo.py:72
Methodstart_training
(self, start_epoch=0, flag=False)
rlkit/torch/algorithms/gcsl/rl.py:72
Methodstart_training
(self, start_epoch=0)
rlkit/torch/algorithms/bc/bc.py:57
Methodstep
Run one timestep of some environments' dynamics. If id is None, run one timestep of all the environments’ dynamics; otherwise run one
rlkit/envs/vecenvs.py:183
Methodstep
(self, actions, *args, **kwargs)
rlkit/envs/envpool.py:17
Methodstep
(self, action)
rlkit/envs/wrappers.py:112
Methodstep
(self, action)
rlkit/envs/wrappers.py:177
Methodstep
(self, action)
rlkit/envs/wrappers.py:240
Methodstep
(self, action)
rlkit/envs/wrappers.py:338
Methodstep
(self, action)
rlkit/envs/wrappers.py:389
Methodstep
(self, action)
rlkit/envs/wrappers.py:441
Methodstep
(self, a)
rlkit/envs/mujoco/ant.py:11
Methodstep
(self, a)
rlkit/envs/mujoco/humanoid.py:37
Methodstep
(self, a)
rlkit/envs/mujoco/walker2d.py:11
Methodstep
(self, a)
rlkit/envs/mujoco/hopper.py:11
Methodstep_tensor
( self, obs: torch.Tensor, act: torch.Tensor, deterministic: bool = False )
rlkit/torch/algorithms/mbpo/fake_env.py:77
Functiontabular_prefix
(key)
rlkit/core/logger.py:270
Methodtask_id_to_obs_task_params
(self, task_id)
rlkit/envs/wrappers.py:260
Methodtask_identifier
(self)
rlkit/envs/wrappers.py:257
Methodtask_params_to_obs_task_params
Sometimes this may be needed. For example if we are training a multitask RL algorithm and want to give it the task params as
rlkit/envs/__init__.py:170
Functiontensor
(*args, torch_device=None, **kwargs)
rlkit/torch/utils/pytorch_util.py:131
Methodterminate_episode
Let the replay buffer know that the episode has terminated in case some special book-keeping has to happen. :return:
rlkit/data_management/episodic_replay_buffer.py:127
Functiontest_build_nested_variant_generator
()
rlkit/launchers/launcher_util.py:467
Functiontest_goal_obs_norm
()
tests/test_obs_norm.py:33
Functiontest_obs_norm
()
tests/test_obs_norm.py:14
Functiontf_like_gather
(x: torch.Tensor, i: torch.Tensor)
rlkit/torch/utils/pytorch_util.py:141
Functiontf_like_gather_np
(x: np.ndarray, i: np.ndarray)
rlkit/torch/utils/pytorch_util.py:146
Methodto
(self, device)
rlkit/torch/algorithms/torch_base_algorithm.py:21
Methodto
(self, device)
rlkit/torch/algorithms/sac/sac_alpha.py:281
Methodto
(self, device)
rlkit/torch/algorithms/her/sac.py:249
Methodto
(self, device)
rlkit/torch/algorithms/ppo/ppo.py:204
← previousnext →701–800 of 830, ranked by callers