MCPcopy Create free account

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

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

↓ 1 callersMethod_get_reward
(self)
multiagent-rl/easy-marl/envs/discrete_meeting.py:84
↓ 1 callersMethod_get_reward
(self)
multiagent-rl/easy-marl/envs/continuous_meeting.py:78
↓ 1 callersMethod_get_reward
(self, reward)
multiagent-rl/easy-marl/envs/discrete_magym/ma_gym_env.py:59
↓ 1 callersMethod_get_reward
(self, reward)
multiagent-rl/easy-marl/envs/continuous_mpe/mpe_env.py:69
↓ 1 callersMethod_get_reward
(self, agent)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/environment.py:143
↓ 1 callersMethod_get_rollout_horizon
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/utility.py:86
↓ 1 callersMethod_get_rollout_horizon
(self)
offline-rl-algorithms/MOPO/mopo_modTH.py:268
↓ 1 callersMethod_get_rollout_horizon
(self)
offline-rl-algorithms/COMBO/mopo_modTH.py:268
↓ 1 callersMethod_get_rollout_horizon
(self)
offline-rl-algorithms/COMBO/combo_modTH.py:278
↓ 1 callersMethod_get_start_obs
(self,rollout_batch_size)
modelbased-rl/BMPO/bmpo.py:366
↓ 1 callersMethod_get_weight
(self, var, LAMBDA, factor=1)
offline-rl-algorithms/UWAC/uwac_impl.py:190
↓ 1 callersMethod_handle_exception
Mark the log directory as finished and call custom fail handler.
modelbased-rl/PlaNet/planet/training/running.py:346
↓ 1 callersMethod_has_finished
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/iterators/base.py:81
↓ 1 callersMethod_has_no_agent
(self, pos)
multiagent-rl/easy-marl/envs/discrete_magym/envs/checkers/checkers.py:151
↓ 1 callersMethod_image_summaries
(self, data, embed, image_pred)
modelbased-rl/Dreamer/ED2-Dreamer/dreamer.py:340
↓ 1 callersMethod_image_summaries
(self, data, embed, image_pred)
modelbased-rl/Dreamer/Vanilla_Dreamer/dreamer.py:300
↓ 1 callersMethod_imagine_ahead
(self, post)
modelbased-rl/Dreamer/ED2-Dreamer/dreamer.py:310
↓ 1 callersMethod_imagine_ahead
(self, post)
modelbased-rl/Dreamer/Vanilla_Dreamer/dreamer.py:270
↓ 1 callersMethod_init_actor_update
Create minimization operations for policy and entropy. Creates a `tf.optimizer.minimize` operations for updating policy and entropy w
modelbased-rl/MBPO/ED2-MBPO/mbpo/algorithms/mbpo.py:565
↓ 1 callersMethod_init_actor_update
Create minimization operations for policy and entropy. Creates a `tf.optimizer.minimize` operations for updating policy and entropy w
modelbased-rl/BMPO/bmpo.py:609
↓ 1 callersMethod_init_critic_update
Create minimization operation for critic Q-function. Creates a `tf.optimizer.minimize` operation for updating critic Q-function with
modelbased-rl/MBPO/ED2-MBPO/mbpo/algorithms/mbpo.py:524
↓ 1 callersMethod_init_critic_update
Create minimization operation for critic Q-function. Creates a `tf.optimizer.minimize` operation for updating critic Q-function with
modelbased-rl/BMPO/bmpo.py:568
↓ 1 callersMethod_init_episode
Initialize environment for new episode. Fills `self._agents`, self._agent_map` and `self._tree_map` with new values.
multiagent-rl/easy-marl/envs/discrete_magym/envs/lumberjacks/lumberjacks.py:135
↓ 1 callersMethod_init_global_step
(self)
modelbased-rl/MBPO/ED2-MBPO/mbpo/algorithms/mbpo.py:444
↓ 1 callersMethod_init_global_step
(self)
modelbased-rl/BMPO/bmpo.py:488
↓ 1 callersMethod_init_necessary_info
(self)
multiagent-rl/easy-marl/algorithms/DDPG_based/IDDPG.py:150
↓ 1 callersMethod_init_necessary_info
(self)
multiagent-rl/easy-marl/algorithms/DDPG_based/MADDPG.py:152
↓ 1 callersMethod_init_necessary_info
(self)
multiagent-rl/easy-marl/algorithms/PPO_based/IPPO.py:134
↓ 1 callersMethod_init_necessary_info
(self)
multiagent-rl/easy-marl/algorithms/PPO_based/MAPPO.py:179
↓ 1 callersMethod_init_necessary_info
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/CommNet.py:143
↓ 1 callersMethod_init_necessary_info
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/QMIX.py:156
↓ 1 callersMethod_init_necessary_info
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/your_new_algorithm.py:63
↓ 1 callersMethod_init_necessary_info
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/VDN.py:126
↓ 1 callersMethod_init_necessary_info
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/IDQN.py:109
↓ 1 callersMethod_init_placeholders
Create input placeholders for the SAC algorithm. Creates `tf.placeholder`s for: - observation - next observation
modelbased-rl/MBPO/ED2-MBPO/mbpo/algorithms/mbpo.py:450
↓ 1 callersMethod_init_placeholders
Create input placeholders for the SAC algorithm. Creates `tf.placeholder`s for: - observation - next observation
modelbased-rl/BMPO/bmpo.py:494
↓ 1 callersMethod_init_training
(self)
modelbased-rl/MBPO/ED2-MBPO/mbpo/algorithms/mbpo.py:640
↓ 1 callersMethod_init_training
(self)
modelbased-rl/BMPO/bmpo.py:690
↓ 1 callersFunction_initial_collection
(config, params)
modelbased-rl/PlaNet/planet/scripts/configs.py:231
↓ 1 callersMethod_is_cell_vacant
(self, pos)
multiagent-rl/easy-marl/envs/discrete_magym/envs/switch/switch_one_corridor.py:117
↓ 1 callersMethod_is_cell_vacant
(self, pos)
multiagent-rl/easy-marl/envs/discrete_magym/envs/traffic_junction/traffic_junction.py:162
↓ 1 callersMethod_is_generating_new_data
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/utility.py:74
↓ 1 callersMethod_is_generating_new_data
(self)
offline-rl-algorithms/MOPO/mopo_modTH.py:257
↓ 1 callersMethod_is_generating_new_data
(self)
offline-rl-algorithms/COMBO/mopo_modTH.py:257
↓ 1 callersMethod_is_generating_new_data
(self)
offline-rl-algorithms/COMBO/combo_modTH.py:267
↓ 1 callersMethod_load_structure
Uses the saved structure in self.model_dir with the name of this network to initialize the structure of this network.
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/bnn.py:582
↓ 1 callersMethod_load_structure
Uses the saved structure in self.model_dir with the name of this network to initialize the structure of this network.
modelbased-rl/BMPO/models/bnn.py:517
↓ 1 callersFunction_log
(config, step_count, log_data, model, replay_buffer, lr, worker_logs, summary_writer)
modelbased-rl/MuZero/core/train.py:25
↓ 1 callersFunction_loss_functions
(config, params)
modelbased-rl/PlaNet/planet/scripts/configs.py:179
↓ 1 callersMethod_mean_communication
(self, hidden_list, layer_index)
multiagent-rl/easy-marl/algorithms/DQN_based/CommNet.py:63
↓ 1 callersFunction_model_components
(config, params)
modelbased-rl/PlaNet/planet/scripts/configs.py:106
↓ 1 callersMethod_mutate_transition
( self, observations: np.ndarray, rewards: np.ndarray, variances: np.ndarray,
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/utility.py:89
↓ 1 callersMethod_mutate_transition
( self, observations: np.ndarray, rewards: np.ndarray, variances: np.ndarray,
offline-rl-algorithms/MOPO/mopo_modTH.py:271
↓ 1 callersMethod_mutate_transition
( self, observations: np.ndarray, rewards: np.ndarray, variances: np.ndarray,
offline-rl-algorithms/COMBO/mopo_modTH.py:271
↓ 1 callersMethod_mutate_transition
( self, observations: np.ndarray, rewards: np.ndarray, variances: np.ndarray,
offline-rl-algorithms/COMBO/combo_modTH.py:281
↓ 1 callersMethod_next
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/iterators/base.py:77
↓ 1 callersMethod_next_pos
Returns next valid position in extended coordinates given by `move` command relative to `curr_pos`.
multiagent-rl/easy-marl/envs/discrete_magym/envs/lumberjacks/lumberjacks.py:318
↓ 1 callersMethod_normal_dist
(self, means, stds)
offline-rl-algorithms/E2O/PEX-main/pex/networks/policy.py:54
↓ 1 callersFunction_normalize_trial_resources
(resources, cpu, gpu, extra_cpu, extra_gpu)
modelbased-rl/MBPO/ED2-MBPO/examples/instrument.py:36
↓ 1 callersMethod_pad_box_space
(self, spaces)
modelbased-rl/PlaNet/planet/control/wrappers.py:419
↓ 1 callersFunction_pad_dims
Append empty dimensions to the tensor until it is of the given rank.
modelbased-rl/PlaNet/planet/tools/overshooting.py:165
↓ 1 callersMethod_predict
( self, x: torch.Tensor, action: torch.Tensor, indices: Optional[torch.Tensor]
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/dynamics/torch/base.py:69
↓ 1 callersMethod_predict_best_action
(self, x: torch.Tensor)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/ddpg_impl.py:193
↓ 1 callersMethod_predict_best_action
(self, x: torch.Tensor)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/plas_impl.py:146
↓ 1 callersMethod_predict_best_action
(self, x: torch.Tensor)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/plas_impl.py:264
↓ 1 callersMethod_predict_value
( self, repeated_x: torch.Tensor, action: torch.Tensor, )
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/bcq_impl.py:189
↓ 1 callersMethod_prepare_logger
( self, save_metrics: bool, experiment_name: Optional[str], with_timestamp: bo
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/base.py:775
↓ 1 callersMethod_reallocate_model_pool
(self)
modelbased-rl/MBPO/ED2-MBPO/mbpo/algorithms/mbpo.py:352
↓ 1 callersMethod_reallocate_model_pool
(self)
modelbased-rl/BMPO/bmpo.py:386
↓ 1 callersMethod_receive
(self)
modelbased-rl/Dreamer/ED2-Dreamer/wrappers.py:449
↓ 1 callersMethod_receive
(self)
modelbased-rl/Dreamer/Vanilla_Dreamer/wrappers.py:434
↓ 1 callersMethod_receive
Wait for a message from the worker process and return its payload. Raises: Exception: An exception was raised inside the worker process.
modelbased-rl/PlaNet/planet/control/wrappers.py:683
↓ 1 callersFunction_remove_prefix
(s, prefix)
offline-rl-algorithms/E2O/PEX-main/pex/utils/util.py:230
↓ 1 callersMethod_reset
(self)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/environment.py:111
↓ 1 callersMethod_reset
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/iterators/base.py:73
↓ 1 callersMethod_restore_replay_pool
(self, current_checkpoint_dir)
modelbased-rl/MBPO/ED2-MBPO/examples/development/main.py:153
↓ 1 callersMethod_rollout_model
(self, rollout_batch_size, **kwargs)
modelbased-rl/MBPO/ED2-MBPO/mbpo/algorithms/mbpo.py:382
↓ 1 callersMethod_rollout_model
(self, rollout_batch_size, **kwargs)
modelbased-rl/BMPO/bmpo.py:420
↓ 1 callersMethod_sample_action
(self, x: torch.Tensor)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/base.py:83
↓ 1 callersMethod_sample_generated_transitions
( self, batch_size: int )
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/iterators/base.py:92
↓ 1 callersMethod_sample_initial_transitions
( self, transitions: List[Transition] )
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/utility.py:77
↓ 1 callersMethod_sample_initial_transitions
( self, transitions: List[Transition] )
offline-rl-algorithms/MOPO/mopo_modTH.py:260
↓ 1 callersMethod_sample_initial_transitions
( self, transitions: List[Transition] )
offline-rl-algorithms/COMBO/mopo_modTH.py:260
↓ 1 callersMethod_sample_initial_transitions
( self, transitions: List[Transition] )
offline-rl-algorithms/COMBO/combo_modTH.py:270
↓ 1 callersMethod_save_best
(self, epoch, holdout_losses)
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/bnn.py:304
↓ 1 callersMethod_save_best
(self, epoch, holdout_losses)
modelbased-rl/BMPO/models/bnn.py:249
↓ 1 callersMethod_save_replay_pool
(self, checkpoint_dir)
modelbased-rl/MBPO/ED2-MBPO/examples/development/main.py:148
↓ 1 callersMethod_save_state
(self, idx)
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/bnn.py:287
↓ 1 callersMethod_save_state
(self, idx)
modelbased-rl/BMPO/models/bnn.py:236
↓ 1 callersMethod_save_stats
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/envs/wrappers.py:354
↓ 1 callersMethod_save_video
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/envs/wrappers.py:343
↓ 1 callersMethod_savefig
(self, label, epoch)
modelbased-rl/MBPO/ED2-MBPO/mbpo/utils/writer.py:57
↓ 1 callersMethod_scalar_summaries
( self, data, feat, prior_dist, post_dist, likes, div, model_loss, value_loss, actor_loss, model_n
modelbased-rl/Dreamer/ED2-Dreamer/dreamer.py:323
↓ 1 callersMethod_scalar_summaries
( self, data, feat, prior_dist, post_dist, likes, div, model_loss, value_loss, actor_loss, model_n
modelbased-rl/Dreamer/Vanilla_Dreamer/dreamer.py:283
↓ 1 callersFunction_serialize_params
(params: Dict[str, Any])
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/base.py:79
↓ 1 callersMethod_set_action
(self, action, agent, action_space, time=None)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/environment.py:149
↓ 1 callersMethod_set_beta
(self)
modelbased-rl/BMPO/bmpo.py:328
↓ 1 callersMethod_set_evaluation_mode
(self)
multiagent-rl/easy-marl/algorithms/DDPG_based/IDDPG.py:204
↓ 1 callersMethod_set_evaluation_mode
(self)
multiagent-rl/easy-marl/algorithms/DDPG_based/MADDPG.py:206
↓ 1 callersMethod_set_evaluation_mode
(self)
multiagent-rl/easy-marl/algorithms/PPO_based/IPPO.py:156
← previousnext →801–900 of 3,230, ranked by callers