索引

A

act() (mindspore_rl.agent.Actor 方法) (mindspore_rl.agent.Agent 方法) action_space (mindspore_rl.environment.Environment property) (mindspore_rl.environment.MsEnvironment property) (mindspore_rl.environment.MultiEnvironmentWrapper property) (mindspore_rl.environment.TicTacToeEnvironment property)

B

batched (mindspore_rl.environment.Environment property) begin() (mindspore_rl.utils.CallbackManager 方法) (mindspore_rl.utils.EvaluateCallback 方法)

boundary (mindspore_rl.environment.Space property)

C

calculate_prior() (mindspore_rl.utils.AlgorithmFunc 方法) (mindspore_rl.utils.VanillaFunc 方法) calculate_rewards() (mindspore_rl.environment.TicTacToeEnvironment 方法) clear() (mindspore_rl.utils.TensorArray 方法) (mindspore_rl.utils.TensorsQueue 方法) close() (mindspore_rl.environment.DeepMindControlEnvironment 方法) (mindspore_rl.environment.Environment 方法) (mindspore_rl.environment.GymEnvironment 方法) (mindspore_rl.environment.MultiEnvironmentWrapper 方法) (mindspore_rl.environment.PettingZooMPEEnvironment 方法) (mindspore_rl.environment.StarCraft2Environment 方法) (mindspore_rl.utils.TensorArray 方法) (mindspore_rl.utils.TensorsQueue 方法) config (mindspore_rl.environment.Environment property) (mindspore_rl.environment.MsEnvironment property) (mindspore_rl.environment.MultiEnvironmentWrapper property) (mindspore_rl.environment.TicTacToeEnvironment property)

construct() (mindspore_rl.network.FullyConnectedLayers 方法) (mindspore_rl.network.FullyConnectedNet 方法) (mindspore_rl.network.GruNet 方法) (mindspore_rl.policy.EpsilonGreedyPolicy 方法) (mindspore_rl.policy.GreedyPolicy 方法) (mindspore_rl.policy.Policy 方法) (mindspore_rl.policy.RandomPolicy 方法) (mindspore_rl.utils.BatchRead 方法) (mindspore_rl.utils.BatchWrite 方法) create_environment() (mindspore_rl.core.MSRL 方法) current_player() (mindspore_rl.environment.TicTacToeEnvironment 方法)

D

destroy() (mindspore_rl.core.PriorityReplayBuffer 方法) (mindspore_rl.utils.MCTS 方法) done_space (mindspore_rl.environment.Environment property) (mindspore_rl.environment.MsEnvironment property) (mindspore_rl.environment.MultiEnvironmentWrapper property) (mindspore_rl.environment.TicTacToeEnvironment property)

E

end() (mindspore_rl.utils.CallbackManager 方法) episode_begin() (mindspore_rl.utils.CallbackManager 方法) (mindspore_rl.utils.TimeCallback 方法) episode_end() (mindspore_rl.utils.CallbackManager 方法) (mindspore_rl.utils.CheckpointCallback 方法) (mindspore_rl.utils.EvaluateCallback 方法) (mindspore_rl.utils.LossCallback 方法) (mindspore_rl.utils.TimeCallback 方法)

evaluate() (mindspore_rl.agent.Trainer 方法)

F

full() (mindspore_rl.core.PriorityReplayBuffer 方法) (mindspore_rl.core.UniformReplayBuffer 方法)

G

get() (mindspore_rl.utils.TensorsQueue 方法) get_action() (mindspore_rl.agent.Actor 方法) (mindspore_rl.agent.Agent 方法)

get_item() (mindspore_rl.core.UniformReplayBuffer 方法) get_replay_buffer() (mindspore_rl.core.MSRL 方法) get_replay_buffer_elements() (mindspore_rl.core.MSRL 方法)

I

init() (mindspore_rl.core.MSRL 方法) insert() (mindspore_rl.core.PriorityReplayBuffer 方法) (mindspore_rl.core.UniformReplayBuffer 方法)

is_discrete (mindspore_rl.environment.Space property) is_terminal() (mindspore_rl.environment.TicTacToeEnvironment 方法)

L

learn() (mindspore_rl.agent.Agent 方法) (mindspore_rl.agent.Learner 方法)

legal_action() (mindspore_rl.environment.TicTacToeEnvironment 方法) load() (mindspore_rl.environment.TicTacToeEnvironment 方法) load_and_eval() (mindspore_rl.agent.Trainer 方法)

M

max_utility() (mindspore_rl.environment.TicTacToeEnvironment 方法) mcts_search() (mindspore_rl.utils.MCTS 方法) mindspore_rl.agent.Actor (內置类) mindspore_rl.agent.Agent (內置类) mindspore_rl.agent.Learner (內置类) mindspore_rl.agent.Trainer (內置类) mindspore_rl.core.MSRL (內置类) mindspore_rl.core.PriorityReplayBuffer (內置类) mindspore_rl.core.Session (內置类) mindspore_rl.core.UniformReplayBuffer (內置类) mindspore_rl.environment.DeepMindControlEnvironment (內置类) mindspore_rl.environment.Environment (內置类) mindspore_rl.environment.EnvironmentProcess (內置类) mindspore_rl.environment.GymEnvironment (內置类) mindspore_rl.environment.MsEnvironment (內置类) mindspore_rl.environment.MultiEnvironmentWrapper (內置类) mindspore_rl.environment.PettingZooMPEEnvironment (內置类) mindspore_rl.environment.Space (內置类) mindspore_rl.environment.StarCraft2Environment (內置类) mindspore_rl.environment.TicTacToeEnvironment (內置类) mindspore_rl.network.FullyConnectedLayers (內置类) mindspore_rl.network.FullyConnectedNet (內置类) mindspore_rl.network.GruNet (內置类)

mindspore_rl.policy.EpsilonGreedyPolicy (內置类) mindspore_rl.policy.GreedyPolicy (內置类) mindspore_rl.policy.Policy (內置类) mindspore_rl.policy.RandomPolicy (內置类) mindspore_rl.utils.AlgorithmFunc (內置类) mindspore_rl.utils.BatchRead (內置类) mindspore_rl.utils.BatchWrite (內置类) mindspore_rl.utils.CallbackManager (內置类) mindspore_rl.utils.CallbackParam (內置类) mindspore_rl.utils.CheckpointCallback (內置类) mindspore_rl.utils.DiscountedReturn (內置类) mindspore_rl.utils.EvaluateCallback (內置类) mindspore_rl.utils.LossCallback (內置类) mindspore_rl.utils.MCTS (內置类) mindspore_rl.utils.OUNoise (內置类) mindspore_rl.utils.SoftUpdate (內置类) mindspore_rl.utils.TensorArray (內置类) mindspore_rl.utils.TensorsQueue (內置类) mindspore_rl.utils.TimeCallback (內置类) mindspore_rl.utils.update_config() 內置函数 mindspore_rl.utils.VanillaFunc (內置类) ms_dtype (mindspore_rl.environment.Space property)

N

np_dtype (mindspore_rl.environment.Space property) num_agent (mindspore_rl.environment.Environment property)

num_environment (mindspore_rl.environment.Environment property) num_values (mindspore_rl.environment.Space property)

O

observation_space (mindspore_rl.environment.Environment property) (mindspore_rl.environment.MsEnvironment property) (mindspore_rl.environment.MultiEnvironmentWrapper property) (mindspore_rl.environment.TicTacToeEnvironment property)

P

pop() (mindspore_rl.utils.TensorsQueue 方法)

put() (mindspore_rl.utils.TensorsQueue 方法)

R

read() (mindspore_rl.utils.TensorArray 方法) recv() (mindspore_rl.environment.Environment 方法) render() (mindspore_rl.environment.Environment 方法) (mindspore_rl.environment.MultiEnvironmentWrapper 方法) reset() (mindspore_rl.core.PriorityReplayBuffer 方法) (mindspore_rl.core.UniformReplayBuffer 方法) (mindspore_rl.environment.Environment 方法) (mindspore_rl.environment.MsEnvironment 方法) (mindspore_rl.environment.MultiEnvironmentWrapper 方法) (mindspore_rl.environment.TicTacToeEnvironment 方法)

restore_tree_data() (mindspore_rl.utils.MCTS 方法) reward_space (mindspore_rl.environment.Environment property) (mindspore_rl.environment.MsEnvironment property) (mindspore_rl.environment.MultiEnvironmentWrapper property) (mindspore_rl.environment.TicTacToeEnvironment property) run() (mindspore_rl.core.Session 方法) (mindspore_rl.environment.EnvironmentProcess 方法)

S

sample() (mindspore_rl.core.PriorityReplayBuffer 方法) (mindspore_rl.core.UniformReplayBuffer 方法) (mindspore_rl.environment.Space 方法) save() (mindspore_rl.environment.TicTacToeEnvironment 方法) send() (mindspore_rl.environment.Environment 方法) set_seed() (mindspore_rl.environment.Environment 方法) shape (mindspore_rl.environment.Space property) simulation() (mindspore_rl.utils.AlgorithmFunc 方法) (mindspore_rl.utils.VanillaFunc 方法)

size() (mindspore_rl.core.UniformReplayBuffer 方法) (mindspore_rl.utils.TensorArray 方法) (mindspore_rl.utils.TensorsQueue 方法) stack() (mindspore_rl.utils.TensorArray 方法) step() (mindspore_rl.environment.Environment 方法) (mindspore_rl.environment.MsEnvironment 方法) (mindspore_rl.environment.MultiEnvironmentWrapper 方法) (mindspore_rl.environment.TicTacToeEnvironment 方法)

T

total_num_player() (mindspore_rl.environment.TicTacToeEnvironment 方法) train() (mindspore_rl.agent.Trainer 方法)

train_one_episode() (mindspore_rl.agent.Trainer 方法) trainable_variables() (mindspore_rl.agent.Trainer 方法)

U

update_priorities() (mindspore_rl.core.PriorityReplayBuffer 方法)

W

write() (mindspore_rl.utils.TensorArray 方法)

內

內置函数 mindspore_rl.utils.update_config()