MCPcopy Create free account

hub / github.com/PKU-MARL/HARL / functions

Functions1,457 in github.com/PKU-MARL/HARL

↓ 4 callersMethodsoft_update
Soft update target actor.
harl/algorithms/actors/off_policy_base.py:28
↓ 4 callersMethodupdate
Update critic network. Args: sample: (Tuple) contains data batch with which to update networks. value_normalizer: (Val
harl/algorithms/critics/v_critic.py:116
↓ 4 callersMethodupdate_property_incr
(sim, discrete_prop, prop, incr_prop)
harl/envs/lag/JSBSim/core/catalog.py:355
↓ 3 callersMethod__init__
(self)
harl/envs/lag/JSBSim/tasks/singlecombat_task.py:331
↓ 3 callersMethod__init__
(self, config)
harl/envs/lag/JSBSim/tasks/singlecombat_with_missle_task.py:14
↓ 3 callersMethod_active_task_one_hot
(self)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/meta_vec_task.py:210
↓ 3 callersMethod_active_task_one_hot
(self)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/multi_task_vec_task.py:207
↓ 3 callersMethodadd_debug_lines
(self, env, pos, rot)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_kettle.py:2074
↓ 3 callersMethodcheck_bounds
Whether a point is within the map bounds.
harl/envs/smac/StarCraft2_Env.py:1062
↓ 3 callersFunctioncompute_hand_reward
( rew_buf, reset_buf, reset_goal_buf, progress_buf, successes, consecutive_successes,
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_meta/shadow_hand_meta_mt4_task_info.py:167
↓ 3 callersMethodcrash
(self)
harl/envs/lag/JSBSim/core/simulatior.py:147
↓ 3 callersFunctionfind_all_files
Find all files under root_dir according to relative pattern.
harl/envs/dexhands/DexterousHands/bidexhands/utils/logger/tools.py:14
↓ 3 callersFunctionget2d_AO_TA_R
(ego_feature, enm_feature, return_side=False)
harl/envs/lag/JSBSim/utils/utils.py:85
↓ 3 callersMethodget_geodetic
(lontitude, latitude, altitude), unit: °, m
harl/envs/lag/JSBSim/core/simulatior.py:48
↓ 3 callersMethodget_global_state
Returns the agent-agnostic global state. NOTE: This functon should not be used during decentralised execution.
harl/envs/smac/StarCraft2_Env.py:1476
↓ 3 callersMethodget_obs
Convert simulation states into the format of observation_space ------ Returns: (np.ndarray) - ego info -
harl/envs/lag/JSBSim/tasks/singlecombat_with_missle_task.py:30
↓ 3 callersMethodget_obs
Returns all agent observat3ions in a list
harl/envs/mamujoco/multiagent_mujoco/mujoco_multi.py:199
↓ 3 callersMethodget_obs_size
Returns the size of the observation.
harl/envs/smac/multiagentenv.py:19
↓ 3 callersMethodget_state
Returns the global state. NOTE: This functon should not be used during decentralised execution.
harl/envs/smac/StarCraft2_Env.py:1276
↓ 3 callersMethodget_state
(self, team=None)
harl/envs/mamujoco/multiagent_mujoco/mujoco_multi.py:240
↓ 3 callersMethodget_state_agent
Returns observation for agent_id. The observation is composed of: - agent movement features (where it can move to, height information and pat
harl/envs/smac/StarCraft2_Env.py:1613
↓ 3 callersMethodget_state_size
Returns the size of the global state.
harl/envs/smac/multiagentenv.py:27
↓ 3 callersMethodget_total_actions
Returns the total number of actions an agent could ever take.
harl/envs/smac/multiagentenv.py:39
↓ 3 callersMethodlog_env
Log environment information.
harl/common/base_logger.py:176
↓ 3 callersMethodlog_train
Log training information.
harl/common/base_logger.py:164
↓ 3 callersMethodrepeat
(self, a)
harl/envs/pettingzoo_mpe/pettingzoo_mpe_env.py:110
↓ 3 callersMethodreset
(self)
harl/envs/lag/JSBSim/envs/singlecombat_env.py:34
↓ 3 callersMethodreset
Reset fighter blood & missile status
harl/envs/lag/JSBSim/tasks/singlecombat_with_missle_task.py:100
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_switch.py:1582
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_bottle_cap.py:1551
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_door_close_inward.py:1598
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_door_close_outward.py:1597
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_catch_over2underarm.py:1334
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_two_catch_underarm.py:1493
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_block_stack.py:1638
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_scissors.py:1606
↓ 3 callersMethodreset_target_pose
(self, env_ids, apply_reset=False)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/allegro_hand_over.py:789
↓ 3 callersMethodreset_target_pose
(self, env_ids, apply_reset=False)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/allegro_hand_catch_underarm.py:806
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_push_block.py:1594
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_kettle.py:1702
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_catch_abreast.py:1363
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_re_orientation.py:1406
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_grasp_and_place.py:1603
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_door_open_outward.py:1594
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_pen.py:1602
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_over.py:1249
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_lift_underarm.py:1461
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_door_open_inward.py:1596
↓ 3 callersMethodreset_target_pose
(self, env_ids, apply_reset=False)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_point_cloud.py:1023
↓ 3 callersMethodreset_target_pose
Reset and randomize the goal pose Args: env_ids (tensor): The index of the environment that needs to reset goal pose
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_catch_underarm.py:1365
↓ 3 callersMethodreset_target_pose
(self, env_ids, apply_reset=False)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_meta/shadow_hand_meta_mt1.py:1189
↓ 3 callersMethodreset_target_pose
(self, env_ids, apply_reset=False)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_meta/shadow_hand_meta_mt4.py:1401
↓ 3 callersMethodreset_target_pose
(self, env_ids, apply_reset=False)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_meta/shadow_hand_meta_ml1.py:1190
↓ 3 callersMethodseed
Sets the seed for this env's random number generator(s). Note: Some environments use multiple pseudorandom number generat
harl/envs/lag/JSBSim/envs/env_base.py:223
↓ 3 callersMethodstep
(self, actions)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/multi_vec_task.py:124
↓ 3 callersMethodstep
(self, env)
harl/envs/lag/JSBSim/tasks/singlecombat_with_missle_task.py:108
↓ 3 callersMethodstep
Task-specific step Args: env: environment instance
harl/envs/lag/JSBSim/tasks/task_base.py:63
↓ 3 callersMethodunit_max_cooldown
Returns the maximal cooldown for a unit.
harl/envs/smac/StarCraft2_Env.py:988
↓ 3 callersFunctionupdate_model
Update the model parameters.
harl/utils/trpo_util.py:36
↓ 2 callersMethod__init__
( self, num_envs, observation_space, share_observation_space, action_space )
harl/envs/env_wrappers.py:64
↓ 2 callersMethod__init__
(self, task, rl_device, clip_observations=5.0, clip_actions=1.0)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/vec_task_rlgames.py:18
↓ 2 callersMethod__init__
(self, task, rl_device, clip_observations=5.0, clip_actions=1.0)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/vec_task.py:18
↓ 2 callersMethod__init__
Constructor. Creates an instance of simulator, initialize all the available properties. Args: uid (str): 5-digits hexadecimal num
harl/envs/lag/JSBSim/core/simulatior.py:18
↓ 2 callersMethod__init__
(self, config)
harl/envs/lag/JSBSim/tasks/multiplecombat_task.py:16
↓ 2 callersMethod_get_obs
(self)
harl/envs/mamujoco/multiagent_mujoco/coupled_half_cheetah.py:45
↓ 2 callersMethod_get_obs
(self)
harl/envs/mamujoco/multiagent_mujoco/manyagent_swimmer.py:87
↓ 2 callersMethod_launch
Launch the StarCraft II game.
harl/envs/smac/StarCraft2_Env.py:348
↓ 2 callersMethod_to_device
Maps all tensors in @inp to this object's device. Args: inp (tensor, iterable, dict): Any primitive data type that inclu
harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/vec_task_rlgames.py:274
↓ 2 callersMethod_unpack
Unpack grouped np.ndarray into seperated key-value dict
harl/envs/lag/JSBSim/envs/env_base.py:256
↓ 2 callersMethod_update_properties
(self)
harl/envs/lag/JSBSim/core/simulatior.py:239
↓ 2 callersMethodadd_debug_lines
(self, env, pos, rot)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_switch.py:1951
↓ 2 callersMethodadd_debug_lines
(self, env, pos, rot)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_block_stack.py:2011
↓ 2 callersMethodadd_debug_lines
(self, env, pos, rot)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_scissors.py:1986
↓ 2 callersMethodadd_debug_lines
(self, env, pos, rot)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/allegro_hand_catch_underarm.py:1082
↓ 2 callersMethodadd_debug_lines
(self, env, pos, rot)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_swing_cup.py:1971
↓ 2 callersMethodadd_debug_lines
(self, env, pos, rot)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_grasp_and_place.py:1962
↓ 2 callersMethodadd_debug_lines
(self, env, pos, rot)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_pen.py:1986
↓ 2 callersFunctioncheck
(input)
harl/envs/lag/JSBSim/model/baseline_actor.py:7
↓ 2 callersMethodclose
Close StarCraft II.
harl/envs/smac/StarCraft2_Env.py:2242
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_switch.py:1194
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_bottle_cap.py:1181
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_door_close_inward.py:1208
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_door_close_outward.py:1208
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_catch_over2underarm.py:949
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_two_catch_underarm.py:1060
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_block_stack.py:1243
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_scissors.py:1218
↓ 2 callersMethodcompute_full_state
(self, asymm_obs=False)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/allegro_hand_over.py:724
↓ 2 callersMethodcompute_full_state
(self, asymm_obs=False)
harl/envs/dexhands/DexterousHands/bidexhands/tasks/allegro_hand_catch_underarm.py:741
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_push_block.py:1203
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_kettle.py:1313
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_catch_abreast.py:975
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_re_orientation.py:1054
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_swing_cup.py:1214
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_grasp_and_place.py:1203
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_door_open_outward.py:1208
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_pen.py:1214
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_over.py:944
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_lift_underarm.py:1073
↓ 2 callersMethodcompute_full_state
Compute the observations of all environment. The observation is composed of three parts: the state values of the left and right hands
harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_door_open_inward.py:1210
← previousnext →101–200 of 1,457, ranked by callers