MCPcopy Create free account

hub / github.com/TJU-DRL-LAB/AI-Optimizer / functions

Functions3,230 in github.com/TJU-DRL-LAB/AI-Optimizer

⨍ Functions 3,230◇ Types & classes 507↳ Endpoints 8
↓ 347 callersMethodappend
(self, experience_dict)
multiagent-rl/easy-marl/buffer.py:27
↓ 137 callersMethodmean
(self)
modelbased-rl/Dreamer/ED2-Dreamer/tools.py:262
↓ 120 callersMethodget
(self, name, ctor, *args, **kwargs)
modelbased-rl/Dreamer/ED2-Dreamer/tools.py:36
↓ 74 callersMethodto
(self, device)
offline-rl-algorithms/E2O/PEX-main/pex/networks/policy.py:83
↓ 73 callersMethodget
(self, key, default=None)
modelbased-rl/PlaNet/planet/tools/attr_dict.py:78
↓ 66 callersMethodappend
Append observation, action, reward and terminal flag to buffer. If the terminal flag is True, Monte-Carlo returns will be computed with
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/online/buffers.py:187
↓ 57 callersMethodstep
( self, action: Union[np.ndarray, int] )
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/envs/wrappers.py:319
↓ 52 callersFunctioncheck_encoder
Checks value and returns EncoderFactory object. Returns: d3rlpy.encoders.EncoderFactory: encoder factory object.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/argument_utility.py:20
↓ 52 callersMethodcopy
Returns a Layer object with the same parameters as this layer. Arguments: sess: (tf.Session/None) session containing the current
modelbased-rl/BMPO/models/fc.py:114
↓ 49 callersMethodeval
Returns stacked observation. Returns: numpy.ndarray: stacked observation.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/preprocessing/stack.py:52
↓ 44 callersMethodlog
Whether the model should compute summaries.
modelbased-rl/PlaNet/planet/training/trainer.py:83
↓ 44 callersMethodrun
(self, root, action_history, model)
modelbased-rl/MuZero/core/mcts.py:66
↓ 41 callersMethodupdate
(self, batch: TorchMiniBatch)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/dqn_impl.py:99
↓ 40 callersMethodcreate
Returns PyTorch's state enocder module. Args: observation_shape: observation shape. Returns: an enocder obje
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/encoders.py:32
↓ 39 callersMethodadd_scalar
(self, label, val, epoch)
modelbased-rl/MBPO/ED2-MBPO/mbpo/utils/writer.py:36
↓ 35 callersMethodseed
(self, seed=None)
modelbased-rl/BMPO/env/pendulum.py:25
↓ 31 callersMethodappend
Appends new data. Args: observations (numpy.ndarray): N-D array. actions (numpy.ndar
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/dataset.py:258
↓ 31 callersMethodload
(self, filename)
modelbased-rl/Dreamer/ED2-Dreamer/tools.py:31
↓ 30 callersMethodget_feature_size
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/encoders.py:18
↓ 26 callersFunctioncheck_use_gpu
Checks value and returns Device object. Returns: d3rlpy.gpu.Device: device object.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/argument_utility.py:96
↓ 26 callersMethodmin
(self, state, action)
offline-rl-algorithms/E2O/PEX-main/pex/networks/value_functions.py:17
↓ 24 callersMethodsample
(self, amount=None)
modelbased-rl/Dreamer/ED2-Dreamer/tools.py:305
↓ 23 callersFunctioncheck_q_func
Checks value and returns QFunctionFactory object. Returns: d3rlpy.q_functions.QFunctionFactory: Q function factory object.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/argument_utility.py:34
↓ 23 callersMethodget
(self, name, ctor, *args, **kwargs)
modelbased-rl/Dreamer/Vanilla_Dreamer/tools.py:35
↓ 22 callersMethodbuild
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/bcq_impl.py:101
↓ 22 callersMethodupdate
(self, observations, actions, next_observations, rewards, terminals)
offline-rl-algorithms/E2O/PEX-main/pex/algorithms/iql.py:40
↓ 20 callersMethodsample_with_log_prob
( self, x: torch.Tensor )
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/policies.py:27
↓ 20 callersMethodupdate_critic_target
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/ddpg_impl.py:201
↓ 19 callersMethodupdate_actor_target
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/ddpg_impl.py:206
↓ 18 callersMethodassign
()
modelbased-rl/PlaNet/planet/tools/streaming_mean.py:65
↓ 18 callersMethoddecode
(self, x: torch.Tensor, latent: torch.Tensor)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/imitators.py:70
↓ 18 callersFunctionfill_cell
(image, pos, cell_size=None, fill='black', margin=0)
multiagent-rl/easy-marl/envs/discrete_magym/envs/utils/draw.py:68
↓ 18 callersMethodstamp
(self)
modelbased-rl/MBPO/ED2-MBPO/mbpo/utils/logging.py:130
↓ 18 callersMethodstep
(self, action_list)
multiagent-rl/easy-marl/envs/base_env.py:18
↓ 17 callersMethodlog_prob
(self, events)
modelbased-rl/Dreamer/ED2-Dreamer/tools.py:295
↓ 17 callersMethodpredict
(self, x: Union[np.ndarray, List[Any]])
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/metrics/scorer.py:18
↓ 17 callersMethodupdate
(self, n=1)
modelbased-rl/MBPO/ED2-MBPO/mbpo/utils/logging.py:30
↓ 16 callersMethodadd
Adds a new layer to the network. Arguments: layer: (layer) The new layer to be added to the network. If this i
modelbased-rl/BMPO/models/bnn.py:109
↓ 16 callersMethodcompute_error
( self, x: torch.Tensor, action: torch.Tensor )
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/imitators.py:130
↓ 16 callersMethodstep
Step the environment. Args: action: The action to apply to the environment. blocking: Whether to wait for the result. Returns:
modelbased-rl/PlaNet/planet/control/wrappers.py:650
↓ 15 callersMethoddevice
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/torch_utility.py:230
↓ 15 callersMethodupdate_actor
( self, batch: TorchMiniBatch )
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/awac_impl.py:80
↓ 15 callersMethodupdate_critic
(self, batch: TorchMiniBatch)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/e2o_impl.py:155
↓ 14 callersMethodexpand
(self, to_play, actions, network_output)
modelbased-rl/MuZero/core/mcts.py:44
↓ 14 callersMethodextend
Extend dataset by another dataset. Args: dataset (d3rlpy.dataset.MDPDataset): dataset.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/dataset.py:326
↓ 14 callersMethodfit
Trains with the given dataset. .. code-block:: python algo.fit(episodes, n_steps=1000000) Args: dataset: li
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/base.py:350
↓ 14 callersMethodpop
Removes and returns the most recently added layer to the network. Returns: (layer) The removed layer.
modelbased-rl/BMPO/models/bnn.py:130
↓ 14 callersMethodreset
Reset the environment. Args: blocking: Whether to wait for the result. Returns: New observation when blocking, otherwise callabl
modelbased-rl/PlaNet/planet/control/wrappers.py:667
↓ 14 callersMethodreset
(self, **kwargs: Any)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/envs/wrappers.py:336
↓ 13 callersFunction_make_batches
( episode: Episode, window_size: int, n_frames: int )
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/metrics/scorer.py:62
↓ 13 callersFunctioncreate_parameter
(shape: Sequence[int], initial_value: float)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/builders.py:200
↓ 13 callersMethodfilter
(x)
offline-rl-algorithms/ISPI/ISPI_C.py:192
↓ 13 callersMethodmeasure_time
(self, name: str)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/logger.py:159
↓ 13 callersMethodsave
Saves all information required to recreate this model in two files in savedir (or self.model_dir if savedir is None), one containing the model
modelbased-rl/BMPO/models/bnn.py:490
↓ 13 callersMethodupdate
(self, n=1)
modelbased-rl/BMPO/utils/logging.py:30
↓ 12 callersMethoddump
Saves dataset as HDF5. Args: fname (str): file path.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/dataset.py:317
↓ 12 callersMethodrun
Run the schedule for a specified number of steps and log scores. Args: max_step: Run the operations until the step reaches this limit.
modelbased-rl/PlaNet/planet/training/trainer.py:152
↓ 12 callersMethodsample
(self, amount=None)
modelbased-rl/Dreamer/Vanilla_Dreamer/tools.py:278
↓ 12 callersMethodsample
Returns sampled mini-batch of transitions. If observation is image, you can stack arbitrary frames via ``n_frames``. .. code
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/online/buffers.py:72
↓ 11 callersMethodseed
(self, seed=None)
modelbased-rl/SampledMuZero/games/lunarlander.py:321
↓ 11 callersMethodset_color
(self, r, g, b, alpha=1)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/rendering.py:167
↓ 10 callersMethodadd_attr
(self, attr)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/rendering.py:165
↓ 10 callersFunctioncreate_squashed_normal_policy
( observation_shape: Sequence[int], action_size: int, encoder_factory: EncoderFactory, min_log
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/builders.py:91
↓ 10 callersFunctionhard_sync
(targ_model: nn.Module, model: nn.Module)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/torch_utility.py:46
↓ 10 callersMethodis_collision
(self, agent1, agent2)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_world_comm.py:126
↓ 10 callersMethodmode
(self)
modelbased-rl/Dreamer/ED2-Dreamer/tools.py:266
↓ 10 callersFunctiontune_help_string
(help_string)
modelbased-rl/MBPO/ED2-MBPO/examples/utils.py:128
↓ 9 callersFunction_get_attributes
(obj: Any)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/torch_utility.py:23
↓ 9 callersMethodadd_metric
(self, name: str, value: float)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/logger.py:110
↓ 9 callersMethodget_weights
(self)
modelbased-rl/MuZero/core/train.py:104
↓ 9 callersMethodis_valid
(self, pos)
multiagent-rl/easy-marl/envs/discrete_magym/envs/predator_prey/predator_prey.py:152
↓ 9 callersMethodlog_probs
(self, x: torch.Tensor)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/policies.py:319
↓ 9 callersMethodstep
(self, action)
modelbased-rl/Dreamer/ED2-Dreamer/wrappers.py:119
↓ 9 callersMethodstep
(self, action)
modelbased-rl/Dreamer/Vanilla_Dreamer/wrappers.py:117
↓ 9 callersFunctionwrite_cell_text
(image, text, pos, cell_size=None, fill='black', margin=0)
multiagent-rl/easy-marl/envs/discrete_magym/envs/utils/draw.py:79
↓ 8 callersMethod__setattr__
(self, name, value)
modelbased-rl/PlaNet/planet/tools/attr_dict.py:48
↓ 8 callersFunction_reduce_ensemble
( y: torch.Tensor, reduction: str = "min", dim: int = 0, lam: float = 0.75 )
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/q_functions/ensemble_q_function.py:12
↓ 8 callersMethod_sample_rollout_action
(self, observations: np.ndarray)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/utility.py:82
↓ 8 callersFunctioncompute_reduce
(value: torch.Tensor, reduction_type: str)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/q_functions/utility.py:64
↓ 8 callersFunctionextract_sub_dict
(prefix, dict)
offline-rl-algorithms/E2O/PEX-main/pex/utils/util.py:228
↓ 8 callersMethodget_output_dim
Returns the dimension of the output. Returns: The dimension of the output.
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/fc.py:186
↓ 8 callersMethodimshow
(self, arr)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/rendering.py:326
↓ 8 callersMethodload
Loads dataset from HDF5. .. code-block:: python import numpy as np from d3rlpy.data
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/dataset.py:366
↓ 8 callersMethodpredict_value
( self, x: Union[np.ndarray, List[Any]], action: Union[np.ndarray, List[Any]],
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/metrics/scorer.py:21
↓ 8 callersMethodset_weights
(self, weights)
modelbased-rl/MuZero/core/train.py:107
↓ 8 callersMethodto_play
Return the current player. Returns: The current player, it should be an element of the players list in the config.
modelbased-rl/SampledMuZero/games/abstract_game.py:26
↓ 8 callersMethodtransform
Returns processed observations. Args: x: observation. Returns: processed observation.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/preprocessing/scalers.py:35
↓ 7 callersMethodcopy
Returns a Layer object with the same parameters as this layer. Arguments: sess: (tf.Session/None) session containing the current
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/fc.py:114
↓ 7 callersMethodcopy
(self, _unlocked=False)
modelbased-rl/PlaNet/planet/tools/attr_dict.py:120
↓ 7 callersFunctiondraw_grid
(rows, cols, cell_size=50, fill='black', line_color='black')
multiagent-rl/easy-marl/envs/discrete_magym/envs/utils/draw.py:32
↓ 7 callersMethodentropy
(self)
modelbased-rl/Dreamer/ED2-Dreamer/tools.py:271
↓ 7 callersMethodget_observation_shape
Returns observation shape. Returns: tuple: observation shape.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/dataset.py:121
↓ 7 callersMethodget_output_dim
Returns the dimension of the output. Returns: The dimension of the output.
modelbased-rl/BMPO/models/fc.py:186
↓ 7 callersMethodget_uniform_network
(self)
modelbased-rl/MuZero/core/config.py:103
↓ 7 callersMethodload
(cls, filename)
modelbased-rl/PlaNet/planet/tools/attr_dict.py:131
↓ 7 callersMethodreset
(self)
multiagent-rl/easy-marl/envs/base_env.py:12
↓ 7 callersMethodto_cpu
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/base.py:134
↓ 7 callersMethodto_gpu
(self, device: Device = Device())
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/base.py:130
↓ 7 callersMethodupdate_temp
( self, batch: TorchMiniBatch )
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/sac_impl.py:128
↓ 6 callersMethod__init__
(self)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/rendering.py:154
next →1–100 of 3,230, ranked by callers