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
↓ 2 callersFunctionmake_polygon
(v, filled=True)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/rendering.py:253
↓ 2 callersFunctionmap_location
(device: str)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/torch_utility.py:130
↓ 2 callersFunctionmass_center
(model, sim)
modelbased-rl/MBPO/ED2-MBPO/mbpo/env/humanoid.py:5
↓ 2 callersMethodmix_q
(self, q_list, state)
multiagent-rl/easy-marl/algorithms/DQN_based/QMIX.py:94
↓ 2 callersMethodmix_q
(self, q_list)
multiagent-rl/easy-marl/algorithms/DQN_based/VDN.py:66
↓ 2 callersMethodnew_game
returns a new instance of the game
modelbased-rl/MuZero/core/config.py:99
↓ 2 callersMethodobs_step
(self, prev_state, prev_action, embed)
modelbased-rl/Dreamer/ED2-Dreamer/models.py:58
↓ 2 callersMethodobs_step
(self, prev_state, prev_action, embed)
modelbased-rl/Dreamer/Vanilla_Dreamer/models.py:58
↓ 2 callersMethodobserve
(self, embed, action, state=None)
modelbased-rl/Dreamer/ED2-Dreamer/models.py:29
↓ 2 callersMethodobserve
(self, embed, action, state=None)
modelbased-rl/Dreamer/Vanilla_Dreamer/models.py:29
↓ 2 callersFunctionovershooting
Perform open loop rollouts from the posteriors at every step. First, we apply the encoder to embed raw inputs and apply the model to obtain poste
modelbased-rl/PlaNet/planet/tools/overshooting.py:28
↓ 2 callersMethodpause
(self)
modelbased-rl/MBPO/ED2-MBPO/mbpo/utils/logging.py:42
↓ 2 callersFunctionplot_summary
Plot lines using matplotlib and create a TensorFlow summary from it. Note that only one instance of this summary can be computed at the same time.
modelbased-rl/PlaNet/planet/tools/summary.py:32
↓ 2 callersMethodpredict
Returns the distribution predicted by the model for each input vector in inputs. Behavior is affected by the dimensionality of inputs and fact
modelbased-rl/BMPO/models/bnn.py:440
↓ 2 callersMethodprediction
(self, encoded_state)
modelbased-rl/SampledMuZero/models.py:112
↓ 2 callersMethodprediction
(self, state)
modelbased-rl/MuZero/core/model.py:23
↓ 2 callersFunctionprint_stats
(path: str)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/cli.py:22
↓ 2 callersMethodrandom_inds
(self, batch_size)
modelbased-rl/BMPO/models/bnn.py:283
↓ 2 callersMethodrecurrent_inference
(self, encoded_state, action)
modelbased-rl/SampledMuZero/models.py:50
↓ 2 callersMethodrecurrent_inference
(self, hidden_state, action)
modelbased-rl/MuZero/core/model.py:41
↓ 2 callersMethodrender
(self, *args, **kwargs)
modelbased-rl/Dreamer/ED2-Dreamer/wrappers.py:61
↓ 2 callersMethodrender
(self, *args, **kwargs)
modelbased-rl/Dreamer/Vanilla_Dreamer/wrappers.py:59
↓ 2 callersMethodreset
Reset the game for a new game. Returns: Initial observation of the game.
modelbased-rl/SampledMuZero/games/atari.py:174
↓ 2 callersMethodreset
(self)
modelbased-rl/MuZero/core/game.py:78
↓ 2 callersMethodresume
(self)
modelbased-rl/MBPO/ED2-MBPO/mbpo/utils/logging.py:36
↓ 2 callersMethodrun
At the root of the search tree we use the representation function to obtain a hidden state given the current observation. We
modelbased-rl/SampledMuZero/self_play.py:256
↓ 2 callersMethodsample_action
BCQ does not support sampling action.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/bcq.py:281
↓ 2 callersMethodsample_action
(self, x: Union[np.ndarray, List[Any]])
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/online/iterators.py:32
↓ 2 callersFunctionsample_batch
(dataset, batch_size)
offline-rl-algorithms/E2O/PEX-main/pex/utils/util.py:128
↓ 2 callersMethodsample_n
(self, x: torch.Tensor, n: int)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/policies.py:32
↓ 2 callersMethodsave_model
(self, fname: str)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/base.py:61
↓ 2 callersMethodsave_model
(self, epoch: int, algo: _SaveProtocol)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/logger.py:151
↓ 2 callersMethodsave_params
(self, logger: D3RLPyLogger)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/online/iterators.py:26
↓ 2 callersMethodscalar_transform
Reference : Appendix F => Network Architecture & Appendix A : Proposition A.2 in https://arxiv.org/pdf/1805.11593.pdf (Page-11)
modelbased-rl/MuZero/core/config.py:110
↓ 2 callersMethodscalar_value_loss
(self, prediction, target)
modelbased-rl/MuZero/config/classic_control/__init__.py:61
↓ 2 callersFunctionselect_action
(node, temperature=1, deterministic=True)
modelbased-rl/MuZero/core/utils.py:35
↓ 2 callersMethodselect_action
Select action according to the visit count distribution and the temperature. The temperature is changed dynamically with the visit_so
modelbased-rl/SampledMuZero/self_play.py:219
↓ 2 callersMethodset_activation
Sets the activation function for this layer. Arguments: activation: (str) The activation function to be used. Returns: N
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/fc.py:219
↓ 2 callersMethodset_activation
Sets the activation function for this layer. Arguments: activation: (str) The activation function to be used. Returns: N
modelbased-rl/BMPO/models/fc.py:219
↓ 2 callersMethodset_active_logger
(self, logger: D3RLPyLogger)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/online/iterators.py:41
↓ 2 callersFunctionset_default_device
Set the default device.
offline-rl-algorithms/E2O/PEX-main/pex/utils/util.py:22
↓ 2 callersMethodset_ensemble_size
(self, ensemble_size)
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/fc.py:266
↓ 2 callersMethodset_input_dim
Sets the dimension of the input. Arguments: input_dim: (int) The dimension of the input. Returns: None
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/fc.py:174
↓ 2 callersMethodset_model_vars
(self, idx, sess, variables)
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/fc.py:60
↓ 2 callersMethodset_output_dim
Sets the dimension of the output. Arguments: output_dim: (int) The dimension of the output. Returns: None.
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/fc.py:193
↓ 2 callersMethodset_output_dim
Sets the dimension of the output. Arguments: output_dim: (int) The dimension of the output. Returns: None.
modelbased-rl/BMPO/models/fc.py:193
↓ 2 callersMethodset_rotation
(self, new)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/rendering.py:190
↓ 2 callersFunctionset_state_dict
(impl: Any, chkpt: Dict[str, Any])
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/torch_utility.py:116
↓ 2 callersMethodsize
(self)
modelbased-rl/MuZero/core/replay_buffer.py:86
↓ 2 callersMethodsize
Returns the number of appended elements in buffer. Returns: the number of elements in buffer.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/online/buffers.py:108
↓ 2 callersMethodstep
(self, a)
modelbased-rl/BMPO/env/ant.py:10
↓ 2 callersMethodstep
(self)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/core.py:184
↓ 2 callersMethodstore_search_statistics
(self, root, action_space)
modelbased-rl/SampledMuZero/self_play.py:492
↓ 2 callersMethodstore_search_stats
(self, root, idx: int = None)
modelbased-rl/MuZero/core/game.py:147
↓ 2 callersFunctionsync_optimizer_state
(targ_optim: Optimizer, optim: Optimizer)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/torch_utility.py:54
↓ 2 callersMethodtermination_fn
(obs, act, next_obs)
modelbased-rl/BMPO/static/ant.py:7
↓ 2 callersFunctiontest
(config, model, episodes, device, render, save_video=False)
modelbased-rl/MuZero/core/test.py:32
↓ 2 callersFunctionto_cpu
(impl: Any)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/torch_utility.py:84
↓ 2 callersFunctionto_cuda
(impl: Any, device: str)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/torch_utility.py:77
↓ 2 callersFunctionto_tensor
(ndarray, volatile=False, requires_grad=False, dtype=FLOAT)
multiagent-rl/easy-marl/buffer.py:13
↓ 2 callersMethodtrain
Trains/Continues network training Arguments: inputs (np.ndarray): Network inputs in the training dataset in rows. tar
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/bnn.py:366
↓ 2 callersMethodtrain
(self, data, log_images=False)
modelbased-rl/Dreamer/ED2-Dreamer/dreamer.py:187
↓ 2 callersMethodtrain
(self, data, log_images=False)
modelbased-rl/Dreamer/Vanilla_Dreamer/dreamer.py:154
↓ 2 callersMethodtrain
Spawn ray workers and launch the training. Args: log_in_tensorboard (bool): Start a testing worker and log its performan
modelbased-rl/SampledMuZero/muzero.py:99
↓ 2 callersMethodtrain
(self, batch_experience_dict)
multiagent-rl/easy-marl/algorithms/DDPG_based/IDDPG.py:105
↓ 2 callersMethodtrain
(self, batch_experience_dict)
multiagent-rl/easy-marl/algorithms/DDPG_based/MADDPG.py:107
↓ 2 callersMethodtrain
(self, batch)
multiagent-rl/easy-marl/algorithms/PPO_based/MAPPO.py:127
↓ 2 callersMethodtrain_one_q_and_pi
(self, replay_buffer, update_a1=True, batch_size=256)
offline-rl-algorithms/ISPI/ISPI_C.py:110
↓ 2 callersFunctiontransform
(dist)
modelbased-rl/PlaNet/planet/training/define_summaries.py:36
↓ 2 callersMethodtransform_numpy
Returns transformed rewards in numpy array. Args: reward: reward. Returns: transformed reward.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/preprocessing/reward_scalers.py:62
↓ 2 callersMethoducb_score
The score for a node is based on its value, plus an exploration bonus based on the prior.
modelbased-rl/SampledMuZero/self_play.py:376
↓ 2 callersMethodupdate
(self, batch: TransitionMiniBatch)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/online/iterators.py:20
↓ 2 callersMethodupdate_actor
(self, batch: TorchMiniBatch)
offline-rl-algorithms/REDQ/redq_impl.py:342
↓ 2 callersMethodupdate_alpha
(self, batch: TorchMiniBatch)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/cql_impl.py:121
↓ 2 callersMethodupdate_critic
(self, batch: TorchMiniBatch)
offline-rl-algorithms/REDQ/redq_impl.py:296
↓ 2 callersMethodupdate_temp
( self, batch: TorchMiniBatch )
offline-rl-algorithms/REDQ/redq_impl.py:125
↓ 2 callersMethodvariables
(self)
modelbased-rl/Dreamer/ED2-Dreamer/tools.py:381
↓ 2 callersMethodzero_state
(self, batch_size, dtype)
modelbased-rl/PlaNet/planet/models/base.py:48
↓ 1 callersMethodQ1
(self, state, action)
offline-rl-algorithms/ISPI/ISPI_S.py:54
↓ 1 callersMethod__call__
(self, x: torch.Tensor)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/imitators.py:126
↓ 1 callersMethod__call__
(self, x: torch.Tensor)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/policies.py:60
↓ 1 callersMethod__call__
( self, x: torch.Tensor, reduction: str = "mean" )
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/q_functions/ensemble_q_function.py:243
↓ 1 callersMethod__check_collision
Verifies if a transition to the position pos will result on a collision. :param pos: position to verify if there is collision
multiagent-rl/easy-marl/envs/discrete_magym/envs/traffic_junction/traffic_junction.py:171
↓ 1 callersMethod__create_grid
(self)
multiagent-rl/easy-marl/envs/discrete_magym/envs/combat/combat.py:173
↓ 1 callersMethod__create_grid
create grid and fill in lemon and apple locations. This grid doesn't fill agents location
multiagent-rl/easy-marl/envs/discrete_magym/envs/checkers/checkers.py:79
↓ 1 callersMethod__create_grid
(self)
multiagent-rl/easy-marl/envs/discrete_magym/envs/pong_duel/pong_duel.py:52
↓ 1 callersMethod__draw_base_img
(self)
multiagent-rl/easy-marl/envs/discrete_magym/envs/predator_prey/predator_prey.py:86
↓ 1 callersMethod__draw_base_img
(self)
multiagent-rl/easy-marl/envs/discrete_magym/envs/combat/combat.py:177
↓ 1 callersMethod__draw_base_img
(self)
multiagent-rl/easy-marl/envs/discrete_magym/envs/switch/switch_one_corridor.py:65
↓ 1 callersMethod__draw_base_img
(self)
multiagent-rl/easy-marl/envs/discrete_magym/envs/checkers/checkers.py:68
↓ 1 callersMethod__draw_base_img
(self)
multiagent-rl/easy-marl/envs/discrete_magym/envs/pong_duel/pong_duel.py:68
↓ 1 callersMethod__eq__
(self, obj: Any)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/gpu.py:63
↓ 1 callersMethod__get_neighbour_coordinates
(self, pos)
multiagent-rl/easy-marl/envs/discrete_magym/envs/predator_prey/predator_prey.py:288
↓ 1 callersMethod__get_next_direction
Computes the new direction vector after the cars turn on the junction for route 2 (turn right) and 3 (turn left) :param route: route
multiagent-rl/easy-marl/envs/discrete_magym/envs/traffic_junction/traffic_junction.py:358
↓ 1 callersMethod__getstate__
(self)
multiagent-rl/easy-marl/utils/read_yaml.py:10
↓ 1 callersMethod__init__
(self, stoch=30, deter=200, hidden=200, act=tf.nn.elu)
modelbased-rl/Dreamer/ED2-Dreamer/models.py:12
↓ 1 callersMethod__init__
(self, name, modules, lr, clip=None, wd=None, wdpattern=r'.*')
modelbased-rl/Dreamer/ED2-Dreamer/tools.py:370
↓ 1 callersMethod__init__
(self, name, modules, lr, clip=None, wd=None, wdpattern=r'.*')
modelbased-rl/Dreamer/Vanilla_Dreamer/tools.py:343
↓ 1 callersMethod__init__
(self)
modelbased-rl/SampledMuZero/models.py:41
↓ 1 callersMethod__init__
(self)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/policy.py:6
← previousnext →501–600 of 3,230, ranked by callers