Index

A

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

Actor (class in mindspore_rl.agent) Agent (class in mindspore_rl.agent) AlgorithmFunc (class in mindspore_rl.utils)

B

batched (mindspore_rl.environment.Environment property) BatchRead (class in mindspore_rl.utils) BatchWrite (class in mindspore_rl.utils)

begin() (mindspore_rl.utils.CallbackManager method) (mindspore_rl.utils.EvaluateCallback method) boundary (mindspore_rl.environment.Space property)

C

calculate_prior() (mindspore_rl.utils.AlgorithmFunc method) (mindspore_rl.utils.VanillaFunc method) calculate_rewards() (mindspore_rl.environment.TicTacToeEnvironment method) CallbackManager (class in mindspore_rl.utils) CallbackParam (class in mindspore_rl.utils) CheckpointCallback (class in mindspore_rl.utils) clear() (mindspore_rl.utils.TensorArray method) (mindspore_rl.utils.TensorsQueue method) close() (mindspore_rl.environment.DeepMindControlEnvironment method) (mindspore_rl.environment.Environment method) (mindspore_rl.environment.GymEnvironment method) (mindspore_rl.environment.MultiEnvironmentWrapper method) (mindspore_rl.environment.PettingZooMPEEnvironment method) (mindspore_rl.environment.StarCraft2Environment method) (mindspore_rl.utils.TensorArray method) (mindspore_rl.utils.TensorsQueue method)

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 method) (mindspore_rl.network.FullyConnectedNet method) (mindspore_rl.network.GruNet method) (mindspore_rl.policy.EpsilonGreedyPolicy method) (mindspore_rl.policy.GreedyPolicy method) (mindspore_rl.policy.Policy method) (mindspore_rl.policy.RandomPolicy method) (mindspore_rl.utils.BatchRead method) (mindspore_rl.utils.BatchWrite method) create_environments() (mindspore_rl.core.MSRL static method) current_player() (mindspore_rl.environment.TicTacToeEnvironment method)

D

DeepMindControlEnvironment (class in mindspore_rl.environment) destroy() (mindspore_rl.core.PriorityReplayBuffer method) (mindspore_rl.utils.MCTS method) DiscountedReturn (class in mindspore_rl.utils)

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 method) Environment (class in mindspore_rl.environment) EnvironmentProcess (class in mindspore_rl.environment) episode_begin() (mindspore_rl.utils.CallbackManager method) (mindspore_rl.utils.TimeCallback method) episode_end() (mindspore_rl.utils.CallbackManager method) (mindspore_rl.utils.CheckpointCallback method) (mindspore_rl.utils.EvaluateCallback method) (mindspore_rl.utils.LossCallback method) (mindspore_rl.utils.TimeCallback method)

EpsilonGreedyPolicy (class in mindspore_rl.policy) evaluate() (mindspore_rl.agent.Trainer method) EvaluateCallback (class in mindspore_rl.utils)

F

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

FullyConnectedLayers (class in mindspore_rl.network) FullyConnectedNet (class in mindspore_rl.network)

G

get() (mindspore_rl.utils.TensorsQueue method) get_action() (mindspore_rl.agent.Actor method) (mindspore_rl.agent.Agent method) get_item() (mindspore_rl.core.UniformReplayBuffer method)

get_replay_buffer() (mindspore_rl.core.MSRL method) get_replay_buffer_elements() (mindspore_rl.core.MSRL method) GreedyPolicy (class in mindspore_rl.policy) GruNet (class in mindspore_rl.network) GymEnvironment (class in mindspore_rl.environment)

I

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

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

L

learn() (mindspore_rl.agent.Agent method) (mindspore_rl.agent.Learner method) Learner (class in mindspore_rl.agent)

legal_action() (mindspore_rl.environment.TicTacToeEnvironment method) load() (mindspore_rl.environment.TicTacToeEnvironment method) load_and_eval() (mindspore_rl.agent.Trainer method) LossCallback (class in mindspore_rl.utils)

M

max_utility() (mindspore_rl.environment.TicTacToeEnvironment method) MCTS (class in mindspore_rl.utils) mcts_search() (mindspore_rl.utils.MCTS method) mindspore_rl module mindspore_rl.agent module mindspore_rl.core module mindspore_rl.environment module mindspore_rl.network module mindspore_rl.policy module

mindspore_rl.utils module module mindspore_rl mindspore_rl.agent mindspore_rl.core mindspore_rl.environment mindspore_rl.network mindspore_rl.policy mindspore_rl.utils ms_dtype (mindspore_rl.environment.Space property) MsEnvironment (class in mindspore_rl.environment) MSRL (class in mindspore_rl.core) MultiEnvironmentWrapper (class in mindspore_rl.environment)

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)

OUNoise (class in mindspore_rl.utils)

P

PettingZooMPEEnvironment (class in mindspore_rl.environment) Policy (class in mindspore_rl.policy)

pop() (mindspore_rl.utils.TensorsQueue method) PriorityReplayBuffer (class in mindspore_rl.core) put() (mindspore_rl.utils.TensorsQueue method)

R

RandomPolicy (class in mindspore_rl.policy) read() (mindspore_rl.utils.TensorArray method) recv() (mindspore_rl.environment.Environment method) render() (mindspore_rl.environment.Environment method) (mindspore_rl.environment.MultiEnvironmentWrapper method) reset() (mindspore_rl.core.PriorityReplayBuffer method) (mindspore_rl.core.UniformReplayBuffer method) (mindspore_rl.environment.Environment method) (mindspore_rl.environment.MsEnvironment method) (mindspore_rl.environment.MultiEnvironmentWrapper method) (mindspore_rl.environment.TicTacToeEnvironment method)

restore_tree_data() (mindspore_rl.utils.MCTS method) 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 method) (mindspore_rl.environment.EnvironmentProcess method)

S

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

size() (mindspore_rl.core.UniformReplayBuffer method) (mindspore_rl.utils.TensorArray method) (mindspore_rl.utils.TensorsQueue method) SoftUpdate (class in mindspore_rl.utils) Space (class in mindspore_rl.environment) stack() (mindspore_rl.utils.TensorArray method) StarCraft2Environment (class in mindspore_rl.environment) step() (mindspore_rl.environment.Environment method) (mindspore_rl.environment.MsEnvironment method) (mindspore_rl.environment.MultiEnvironmentWrapper method) (mindspore_rl.environment.TicTacToeEnvironment method)

T

TensorArray (class in mindspore_rl.utils) TensorsQueue (class in mindspore_rl.utils) TicTacToeEnvironment (class in mindspore_rl.environment) TimeCallback (class in mindspore_rl.utils)

total_num_player() (mindspore_rl.environment.TicTacToeEnvironment method) train() (mindspore_rl.agent.Trainer method) train_one_episode() (mindspore_rl.agent.Trainer method) trainable_variables() (mindspore_rl.agent.Trainer method) Trainer (class in mindspore_rl.agent)

U

UniformReplayBuffer (class in mindspore_rl.core)

update_config() (in module mindspore_rl.utils) update_priorities() (mindspore_rl.core.PriorityReplayBuffer method)

V

VanillaFunc (class in mindspore_rl.utils)

W

write() (mindspore_rl.utils.TensorArray method)