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
↓ 1 callersMethod_set_evaluation_mode
(self)
multiagent-rl/easy-marl/algorithms/PPO_based/MAPPO.py:213
↓ 1 callersMethod_set_evaluation_mode
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/CommNet.py:181
↓ 1 callersMethod_set_evaluation_mode
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/QMIX.py:195
↓ 1 callersMethod_set_evaluation_mode
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/your_new_algorithm.py:101
↓ 1 callersMethod_set_evaluation_mode
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/VDN.py:164
↓ 1 callersMethod_set_evaluation_mode
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/IDQN.py:147
↓ 1 callersMethod_set_rollout_length
(self)
modelbased-rl/MBPO/ED2-MBPO/mbpo/algorithms/mbpo.py:338
↓ 1 callersMethod_set_rollout_length
(self)
modelbased-rl/BMPO/bmpo.py:338
↓ 1 callersMethod_set_state
(self)
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/bnn.py:291
↓ 1 callersMethod_set_state
(self)
modelbased-rl/BMPO/models/bnn.py:239
↓ 1 callersMethod_set_train_mode
(self)
multiagent-rl/easy-marl/algorithms/DDPG_based/IDDPG.py:200
↓ 1 callersMethod_set_train_mode
(self)
multiagent-rl/easy-marl/algorithms/DDPG_based/MADDPG.py:202
↓ 1 callersMethod_set_train_mode
(self)
multiagent-rl/easy-marl/algorithms/PPO_based/IPPO.py:153
↓ 1 callersMethod_set_train_mode
(self)
multiagent-rl/easy-marl/algorithms/PPO_based/MAPPO.py:209
↓ 1 callersMethod_set_train_mode
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/CommNet.py:178
↓ 1 callersMethod_set_train_mode
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/QMIX.py:192
↓ 1 callersMethod_set_train_mode
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/your_new_algorithm.py:98
↓ 1 callersMethod_set_train_mode
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/VDN.py:161
↓ 1 callersMethod_set_train_mode
(self)
multiagent-rl/easy-marl/algorithms/DQN_based/IDQN.py:144
↓ 1 callersMethod_should_resume
Determine whether the run can be resumed. Returns: Boolean whether to resume the run.
modelbased-rl/PlaNet/planet/training/running.py:232
↓ 1 callersMethod_should_start
Determine whether a run can be started. Returns: Boolean whether to start the run.
modelbased-rl/PlaNet/planet/training/running.py:218
↓ 1 callersMethod_simulate_one_step
(self, action_list)
multiagent-rl/easy-marl/envs/discrete_meeting.py:77
↓ 1 callersMethod_simulate_one_step
(self, action_list)
multiagent-rl/easy-marl/envs/continuous_meeting.py:72
↓ 1 callersMethod_start_train
(self)
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/bnn.py:328
↓ 1 callersMethod_start_train
(self)
modelbased-rl/BMPO/models/bnn.py:273
↓ 1 callersMethod_step
(self, action_n)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/environment.py:84
↓ 1 callersMethod_store_checkpoint
Store a checkpoint if a log directory was provided to the constructor. The directory will be created if needed. Args: sess: Session co
modelbased-rl/PlaNet/planet/training/trainer.py:326
↓ 1 callersMethod_store_fail
Mark run as failed by writing a FAIL file.
modelbased-rl/PlaNet/planet/training/running.py:278
↓ 1 callersFunction_tasks
(config, params)
modelbased-rl/PlaNet/planet/scripts/configs.py:154
↓ 1 callersMethod_to_extended_coordinates
Translate relative coordinates in to the extended coordinates.
multiagent-rl/easy-marl/envs/discrete_magym/envs/lumberjacks/lumberjacks.py:163
↓ 1 callersMethod_to_relative_coordinates
Translate extended coordinates in to the relative coordinates.
multiagent-rl/easy-marl/envs/discrete_magym/envs/lumberjacks/lumberjacks.py:167
↓ 1 callersFunction_train
(config, shared_storage, replay_buffer, summary_writer)
modelbased-rl/MuZero/core/train.py:286
↓ 1 callersMethod_train
Return a generator that performs RL training. Args: env (`SoftlearningEnv`): Environment used for training. policy (`
modelbased-rl/MBPO/ED2-MBPO/mbpo/algorithms/mbpo.py:169
↓ 1 callersMethod_train
(self)
modelbased-rl/BMPO/bmpo.py:208
↓ 1 callersMethod_train_model
(self, **kwargs)
modelbased-rl/MBPO/ED2-MBPO/mbpo/algorithms/mbpo.py:376
↓ 1 callersMethod_train_model
(self, **kwargs)
modelbased-rl/BMPO/bmpo.py:410
↓ 1 callersMethod_train_target_network_soft
(self)
multiagent-rl/easy-marl/algorithms/DDPG_based/IDDPG.py:182
↓ 1 callersMethod_train_target_network_soft
(self)
multiagent-rl/easy-marl/algorithms/DDPG_based/MADDPG.py:184
↓ 1 callersMethod_training_batch
(self, batch_size=None)
modelbased-rl/BMPO/bmpo.py:469
↓ 1 callersFunction_training_schedule
(config, params)
modelbased-rl/PlaNet/planet/scripts/configs.py:202
↓ 1 callersMethod_update
(self, batch: TransitionMiniBatch)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/base.py:756
↓ 1 callersMethod_update_agent_pos
Moves `agent` according the `move` command.
multiagent-rl/easy-marl/envs/discrete_magym/envs/lumberjacks/lumberjacks.py:307
↓ 1 callersMethod_write
(self, episode, filename)
modelbased-rl/PlaNet/planet/control/wrappers.py:512
↓ 1 callersMethod_write_summaries
(self)
modelbased-rl/Dreamer/ED2-Dreamer/dreamer.py:353
↓ 1 callersMethod_write_summaries
(self)
modelbased-rl/Dreamer/Vanilla_Dreamer/dreamer.py:313
↓ 1 callersMethodact
(self, obs, deterministic=False, enable_grad=False)
offline-rl-algorithms/E2O/PEX-main/pex/networks/policy.py:78
↓ 1 callersMethodaction_space
(self)
modelbased-rl/MuZero/core/game.py:53
↓ 1 callersMethodadd
(self, state, action, next_state, reward, done)
offline-rl-algorithms/ISPI/utils.py:19
↓ 1 callersMethodadd_action
(self, action: Action)
modelbased-rl/MuZero/core/game.py:47
↓ 1 callersFunctionadd_command_line_args_to_variant_spec
(variant_spec, command_line_args)
modelbased-rl/MBPO/ED2-MBPO/examples/instrument.py:55
↓ 1 callersMethodadd_exploration_noise
At the start of each search, we add dirichlet noise to the prior of the root to encourage the search to explore new actions.
modelbased-rl/SampledMuZero/self_play.py:463
↓ 1 callersMethodadd_exploration_noise
(self, dirichlet_alpha, exploration_fraction)
modelbased-rl/MuZero/core/mcts.py:54
↓ 1 callersMethodadd_generated_transitions
(self, transitions: List[Transition])
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/iterators/base.py:84
↓ 1 callersFunctionadd_headers
(directory, header)
modelbased-rl/PlaNet/planet/scripts/sync.py:61
↓ 1 callersMethodadd_params
(self, params: Dict[str, Any])
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/logger.py:88
↓ 1 callersFunctionadd_ray_init_args
(parser)
modelbased-rl/MBPO/ED2-MBPO/examples/utils.py:90
↓ 1 callersFunctionadd_ray_tune_args
(parser)
modelbased-rl/MBPO/ED2-MBPO/examples/utils.py:126
↓ 1 callersMethodadd_saver
Add a saver to save or load variables. Args: include: One or more regexes to match variable names to include. exclude: One or more re
modelbased-rl/PlaNet/planet/training/trainer.py:92
↓ 1 callersFunctionadjust_lr
(config, optimizer, step_count)
modelbased-rl/MuZero/core/train.py:278
↓ 1 callersMethodadversaries
(self, world)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_adversary.py:73
↓ 1 callersMethodadversaries
(self, world)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_crypto.py:90
↓ 1 callersMethodadversary_reward
(self, agent, world)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_adversary.py:109
↓ 1 callersMethodadversary_reward
(self, agent, world)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_world_comm.py:185
↓ 1 callersMethodadversary_reward
(self, agent, world)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_crypto.py:115
↓ 1 callersMethodadversary_reward
(self, agent, world)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_tag.py:115
↓ 1 callersMethodadversary_reward
(self, agent, world)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_push.py:74
↓ 1 callersMethodagent_reward
(self, agent, world)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_adversary.py:80
↓ 1 callersMethodagent_reward
(self, agent, world)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_world_comm.py:155
↓ 1 callersMethodagent_reward
(self, agent, world)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_crypto.py:96
↓ 1 callersMethodagent_reward
(self, agent, world)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_tag.py:89
↓ 1 callersMethodagent_reward
(self, agent, world)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/scenarios/simple_push.py:70
↓ 1 callersFunctionaggregate_summaries
(logdir: str, exp_path: str, )
modelbased-rl/MuZero/scripts/aggregate_summaries.py:6
↓ 1 callersFunctionangle_normalize
(x)
modelbased-rl/BMPO/env/pendulum.py:89
↓ 1 callersMethodappend
(self, item: T)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/containers.py:38
↓ 1 callersMethodappend_description
(self, descr)
modelbased-rl/MBPO/ED2-MBPO/mbpo/utils/logging.py:78
↓ 1 callersMethodappend_description
(self, descr)
modelbased-rl/BMPO/utils/logging.py:77
↓ 1 callersMethodappend_episode
Append Episode object to buffer. Args: episode: episode.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/online/buffers.py:59
↓ 1 callersMethodapply_action_force
(self, p_force)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/core.py:205
↓ 1 callersMethodapply_environment_force
(self, p_force)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/core.py:214
↓ 1 callersMethodbackpropagate
At the end of a simulation, we propagate the evaluation all the way up the tree to the root.
modelbased-rl/SampledMuZero/self_play.py:402
↓ 1 callersMethodbackpropagate
(self, search_path, value, to_play, min_max_stats)
modelbased-rl/MuZero/core/mcts.py:107
↓ 1 callersFunctionbaseline
(index, method, ax, runs, args)
modelbased-rl/Dreamer/Vanilla_Dreamer/plotting.py:204
↓ 1 callersMethodbegin_episode
(self, agent_indices)
modelbased-rl/PlaNet/planet/control/mpc_agent.py:45
↓ 1 callersMethodboltzmann
(self, x, temperature)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/sac_impl.py:167
↓ 1 callersMethodbuild
(self)
modelbased-rl/BMPO/runner.py:27
↓ 1 callersMethodbuild
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/plas_impl.py:93
↓ 1 callersMethodbuild
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/dynamics/torch/probabilistic_ensemble_dynamics_impl.py:63
↓ 1 callersMethodbuild
(self)
offline-rl-algorithms/UWAC/uwac_impl.py:156
↓ 1 callersMethodbuild
(self)
offline-rl-algorithms/MOPO/sac_modTH_impl.py:104
↓ 1 callersMethodbuild_with_env
(self, env: gym.Env)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/online/iterators.py:23
↓ 1 callersMethodcache
Caches current values of this scaler. Returns: None.
modelbased-rl/MBPO/ED2-MBPO/mbpo/models/utils.py:84
↓ 1 callersMethodcache
Caches current values of this scaler. Returns: None.
modelbased-rl/BMPO/models/utils.py:84
↓ 1 callersMethodcalculate_distances
(self)
multiagent-rl/easy-marl/envs/continuous_mpe/multiagent/core.py:143
↓ 1 callersFunctioncheck_action_scaler
Checks value and returns Scaler object. Returns: action scaler object.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/argument_utility.py:64
↓ 1 callersFunctioncheck_reward_scaler
Checks value and returns Scaler object. Returns: reward scaler object.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/argument_utility.py:80
↓ 1 callersFunctioncheck_scaler
Checks value and returns Scaler object. Returns: scaler object.
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/argument_utility.py:48
↓ 1 callersFunctionclear_monitor_files
(training_dir)
multiagent-rl/easy-marl/envs/discrete_magym/wrappers/monitor.py:98
↓ 1 callersFunctioncli
(data_path, kwargs)
modelbased-rl/MBPO/ED2-MBPO/mbpo/scripts/console_scripts.py:6
↓ 1 callersMethodclip_episode
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/online/buffers.py:314
↓ 1 callersMethodclone
(self)
modelbased-rl/MuZero/core/game.py:44
← previousnext →901–1,000 of 3,230, ranked by callers