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__init__
(self, args)
multiagent-rl/easy-marl/algorithms/DQN_based/QMIX.py:61
↓ 1 callersMethod__init__
(self, args)
multiagent-rl/easy-marl/algorithms/DQN_based/your_new_algorithm.py:42
↓ 1 callersMethod__init__
(self, args)
multiagent-rl/easy-marl/algorithms/DQN_based/VDN.py:33
↓ 1 callersMethod__init__
(self, state_dim, hidden_dim=256, n_hidden=2)
offline-rl-algorithms/E2O/PEX-main/pex/networks/value_functions.py:22
↓ 1 callersMethod__init__
( self, *, actor_learning_rate: float = 1e-4, critic_learning_rate: float = 3e
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/cql.py:136
↓ 1 callersMethod__init__
( self, *, distribution: str = "uniform", normal_std: float = 1.0, act
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/random_policy.py:30
↓ 1 callersMethod__init__
( self, *, actor_learning_rate: float = 3e-4, critic_learning_rate: float = 3e
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/sac.py:118
↓ 1 callersMethod__init__
( self, *, actor_learning_rate: float = 1e-3, critic_learning_rate: float = 1e
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/bcq.py:168
↓ 1 callersMethod__init__
( self, *, actor_learning_rate: float = 1e-4, critic_learning_rate: float = 1e
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/plas.py:102
↓ 1 callersMethod__init__
( self, observation_shape: Sequence[int], action_size: int, actor_learning_rat
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/bcq_impl.py:44
↓ 1 callersMethod__init__
( self, observation_shape: Sequence[int], action_size: int, actor_learning_rat
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/sac_impl.py:44
↓ 1 callersMethod__init__
( self, observation_shape: Sequence[int], action_size: int, actor_learning_rat
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/cql_impl.py:33
↓ 1 callersMethod__init__
( self, observation_shape: Sequence[int], action_size: int, actor_learning_rat
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/plas_impl.py:40
↓ 1 callersMethod__init__
(self, encoder: EncoderWithAction)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/dynamics.py:63
↓ 1 callersMethod__init__
(self, encoder: Encoder, action_size: int, n_quantiles: int)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/q_functions/qr_q_function.py:28
↓ 1 callersMethod__init__
( self, encoder: Encoder, action_size: int, n_quantiles: int, n_greedy
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/q_functions/iqn_q_function.py:59
↓ 1 callersMethod__init__
( self, encoder: Encoder, action_size: int, n_quantiles: int, embed_si
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/q_functions/fqf_q_function.py:47
↓ 1 callersMethod__init__
(self, encoder: Encoder, action_size: int)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/q_functions/mean_q_function.py:17
↓ 1 callersMethod__init__
( self, maxlen: int, env: Optional[gym.Env] = None, episodes: Optional[List[Ep
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/online/buffers.py:25
↓ 1 callersMethod__init__
( self, observation_shape: Sequence[int], action_size: int, actor_learning_rat
offline-rl-algorithms/REDQ/redq_impl.py:44
↓ 1 callersMethod__init__
( self, *, actor_learning_rate: float = 3e-4, critic_learning_rate: float = 3e
offline-rl-algorithms/REDQ/redq.py:41
↓ 1 callersMethod__init__
( self, observation_shape: Sequence[int], action_size: int, actor_learning_rat
offline-rl-algorithms/COMBO/t.py:44
↓ 1 callersMethod__init_full_obs
(self)
multiagent-rl/easy-marl/envs/discrete_magym/envs/predator_prey/predator_prey.py:93
↓ 1 callersMethod__init_full_obs
Each team consists of m = 5 agents and their initial positions are sampled uniformly in a 5 × 5 square around the team center, which is picke
multiagent-rl/easy-marl/envs/discrete_magym/envs/combat/combat.py:188
↓ 1 callersMethod__init_full_obs
(self)
multiagent-rl/easy-marl/envs/discrete_magym/envs/checkers/checkers.py:92
↓ 1 callersMethod__init_full_obs
Initiates environment: inserts up to |entry_gates| cars. once the entry gates are filled, the remaining agents stay initialized outsi
multiagent-rl/easy-marl/envs/discrete_magym/envs/traffic_junction/traffic_junction.py:138
↓ 1 callersMethod__init_full_obs
(self)
multiagent-rl/easy-marl/envs/discrete_magym/envs/pong_duel/pong_duel.py:72
↓ 1 callersMethod__is_agent_done
(self, agent_i)
multiagent-rl/easy-marl/envs/discrete_magym/envs/switch/switch_one_corridor.py:147
↓ 1 callersMethod__is_gate_free
Verifies if any spawning gate is free for a car to be placed :return: list of currently free gates :rtype: list
multiagent-rl/easy-marl/envs/discrete_magym/envs/traffic_junction/traffic_junction.py:182
↓ 1 callersMethod__next_pos
(self, curr_pos, move)
multiagent-rl/easy-marl/envs/discrete_magym/envs/predator_prey/predator_prey.py:180
↓ 1 callersMethod__reached_dest
Verifies if the agent_i reached a destination place. :param agent_i: id of the agent :type agent_i: int :return: boo
multiagent-rl/easy-marl/envs/discrete_magym/envs/traffic_junction/traffic_junction.py:195
↓ 1 callersMethod__setstate__
(self, state)
multiagent-rl/easy-marl/utils/read_yaml.py:13
↓ 1 callersMethod__update_agent_pos
(self, agent_i, move)
multiagent-rl/easy-marl/envs/discrete_magym/envs/predator_prey/predator_prey.py:158
↓ 1 callersMethod__update_agent_pos
(self, agent_i, move)
multiagent-rl/easy-marl/envs/discrete_magym/envs/combat/combat.py:277
↓ 1 callersMethod__update_agent_pos
(self, agent_i, move)
multiagent-rl/easy-marl/envs/discrete_magym/envs/switch/switch_one_corridor.py:121
↓ 1 callersMethod__update_agent_pos
(self, agent_i, move)
multiagent-rl/easy-marl/envs/discrete_magym/envs/checkers/checkers.py:154
↓ 1 callersMethod__update_agent_pos
Updates the agent position in the environment. Moves can be 0 (GAS) or 1 (BRAKE). If the move is 1 does nothing, car remains stopped.
multiagent-rl/easy-marl/envs/discrete_magym/envs/traffic_junction/traffic_junction.py:378
↓ 1 callersMethod__update_agent_pos
(self, agent_i, move)
multiagent-rl/easy-marl/envs/discrete_magym/envs/pong_duel/pong_duel.py:163
↓ 1 callersMethod__update_ball_pos
(self)
multiagent-rl/easy-marl/envs/discrete_magym/envs/pong_duel/pong_duel.py:180
↓ 1 callersMethod__update_ball_view
(self)
multiagent-rl/easy-marl/envs/discrete_magym/envs/pong_duel/pong_duel.py:65
↓ 1 callersMethod__update_opp_pos
(self, opp_i, move)
multiagent-rl/easy-marl/envs/discrete_magym/envs/combat/combat.py:300
↓ 1 callersMethod__update_prey_pos
(self, prey_i, move)
multiagent-rl/easy-marl/envs/discrete_magym/envs/predator_prey/predator_prey.py:193
↓ 1 callersMethod__wall_exists
(self, pos)
multiagent-rl/easy-marl/envs/discrete_magym/envs/switch/switch_one_corridor.py:113
↓ 1 callersMethod_add_label
(self, data, label)
modelbased-rl/MBPO/ED2-MBPO/mbpo/utils/writer.py:32
↓ 1 callersMethod_add_last_step
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/online/buffers.py:321
↓ 1 callersMethod_agent_view_generator
Yields position, number of agent and tree strength for cells in distance of `view_range` from `pos`.
multiagent-rl/easy-marl/envs/discrete_magym/envs/lumberjacks/lumberjacks.py:263
↓ 1 callersFunction_apply_spectral_norm_recursively
(model: nn.Module)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/models/torch/dynamics.py:28
↓ 1 callersMethod_backward_policy_net
(self, scope, state,action_dim,hidden_dim = 256)
modelbased-rl/BMPO/bmpo.py:186
↓ 1 callersMethod_build
(self)
modelbased-rl/MBPO/ED2-MBPO/mbpo/algorithms/mbpo.py:161
↓ 1 callersMethod_build
(self)
modelbased-rl/MBPO/ED2-MBPO/examples/development/main.py:41
↓ 1 callersMethod_build
(self)
modelbased-rl/BMPO/bmpo.py:159
↓ 1 callersMethod_build_actor
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/sac_impl.py:300
↓ 1 callersMethod_build_actor
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/ddpg_impl.py:129
↓ 1 callersMethod_build_actor
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/plas_impl.py:99
↓ 1 callersMethod_build_actor
(self)
offline-rl-algorithms/REDQ/redq_impl.py:271
↓ 1 callersMethod_build_actor
(self)
offline-rl-algorithms/COMBO/t.py:271
↓ 1 callersMethod_build_actor_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/sac_impl.py:307
↓ 1 callersMethod_build_actor_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/ddpg_impl.py:132
↓ 1 callersMethod_build_actor_optim
(self)
offline-rl-algorithms/REDQ/redq_impl.py:278
↓ 1 callersMethod_build_actor_optim
(self)
offline-rl-algorithms/COMBO/t.py:278
↓ 1 callersMethod_build_alpha
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/cql_impl.py:100
↓ 1 callersMethod_build_alpha
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/bear_impl.py:160
↓ 1 callersMethod_build_alpha
(self)
offline-rl-algorithms/UWAC/uwac_impl.py:180
↓ 1 callersMethod_build_alpha_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/cql_impl.py:104
↓ 1 callersMethod_build_alpha_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/bear_impl.py:164
↓ 1 callersMethod_build_alpha_optim
(self)
offline-rl-algorithms/UWAC/uwac_impl.py:184
↓ 1 callersMethod_build_backward_policy
(self,act_dim)
modelbased-rl/BMPO/bmpo.py:168
↓ 1 callersMethod_build_critic
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/sac_impl.py:285
↓ 1 callersMethod_build_critic
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/ddpg_impl.py:113
↓ 1 callersMethod_build_critic
(self)
offline-rl-algorithms/REDQ/redq_impl.py:256
↓ 1 callersMethod_build_critic
(self)
offline-rl-algorithms/COMBO/t.py:256
↓ 1 callersMethod_build_critic_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/sac_impl.py:294
↓ 1 callersMethod_build_critic_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/ddpg_impl.py:122
↓ 1 callersMethod_build_critic_optim
(self)
offline-rl-algorithms/REDQ/redq_impl.py:265
↓ 1 callersMethod_build_critic_optim
(self)
offline-rl-algorithms/COMBO/t.py:265
↓ 1 callersMethod_build_dynamics
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/dynamics/torch/probabilistic_ensemble_dynamics_impl.py:72
↓ 1 callersMethod_build_imitator
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/bcq_impl.py:115
↓ 1 callersMethod_build_imitator
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/plas_impl.py:106
↓ 1 callersMethod_build_imitator
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/bear_impl.py:143
↓ 1 callersMethod_build_imitator
(self)
offline-rl-algorithms/UWAC/uwac_impl.py:163
↓ 1 callersMethod_build_imitator_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/bcq_impl.py:126
↓ 1 callersMethod_build_imitator_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/plas_impl.py:117
↓ 1 callersMethod_build_imitator_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/bear_impl.py:154
↓ 1 callersMethod_build_imitator_optim
(self)
offline-rl-algorithms/UWAC/uwac_impl.py:174
↓ 1 callersMethod_build_model
(self)
modelbased-rl/Dreamer/ED2-Dreamer/dreamer.py:247
↓ 1 callersMethod_build_model
(self)
modelbased-rl/Dreamer/Vanilla_Dreamer/dreamer.py:214
↓ 1 callersMethod_build_network
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/ope/torch/fqe_impl.py:92
↓ 1 callersMethod_build_network
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/bc_impl.py:77
↓ 1 callersMethod_build_network
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/dqn_impl.py:82
↓ 1 callersMethod_build_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/ope/torch/fqe_impl.py:95
↓ 1 callersMethod_build_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/bc_impl.py:80
↓ 1 callersMethod_build_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/dqn_impl.py:91
↓ 1 callersMethod_build_optim
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/dynamics/torch/probabilistic_ensemble_dynamics_impl.py:81
↓ 1 callersMethod_build_temperature
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/sac_impl.py:104
↓ 1 callersMethod_build_temperature
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/sac_impl.py:313
↓ 1 callersMethod_build_temperature
(self)
offline-rl-algorithms/E2O/d3rlpy_new/d3rlpy/algos/torch/e2o_impl.py:94
↓ 1 callersMethod_build_temperature
(self)
offline-rl-algorithms/REDQ/redq_impl.py:104
↓ 1 callersMethod_build_temperature
(self)
offline-rl-algorithms/REDQ/redq_impl.py:284
↓ 1 callersMethod_build_temperature
(self)
offline-rl-algorithms/MOPO/sac_modTH_impl.py:116
↓ 1 callersMethod_build_temperature
(self)
offline-rl-algorithms/COMBO/sac_modTH_impl.py:116
← previousnext →601–700 of 3,230, ranked by callers