Index

A

act() (mindspore_rl.agent.Actor method) (mindspore_rl.agent.Agent method) act_init() (mindspore_rl.agent.Actor method) action_space (mindspore_rl.environment.Environment property) (mindspore_rl.environment.GymEnvironment property) (mindspore_rl.environment.MsEnvironment property) (mindspore_rl.environment.MultiEnvironmentWrapper property) (mindspore_rl.environment.StarCraft2Environment property) (mindspore_rl.environment.TicTacToeEnvironment property)

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

B

boundary (mindspore_rl.environment.Space property)

C

calculate_rewards() (mindspore_rl.environment.TicTacToeEnvironment method) config (mindspore_rl.environment.Environment property) (mindspore_rl.environment.GymEnvironment property) (mindspore_rl.environment.MsEnvironment property) (mindspore_rl.environment.MultiEnvironmentWrapper property) (mindspore_rl.environment.StarCraft2Environment 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) current_player() (mindspore_rl.environment.TicTacToeEnvironment method)

D

destroy() (mindspore_rl.core.PriorityReplayBuffer method) done_space (mindspore_rl.environment.Environment property) (mindspore_rl.environment.GymEnvironment property) (mindspore_rl.environment.MsEnvironment property) (mindspore_rl.environment.MultiEnvironmentWrapper property) (mindspore_rl.environment.StarCraft2Environment property) (mindspore_rl.environment.TicTacToeEnvironment property)

E

Environment (class in mindspore_rl.environment) EnvironmentProcess (class in mindspore_rl.environment)

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

F

full() (mindspore_rl.core.ReplayBuffer method)

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

G

get_action() (mindspore_rl.agent.Actor method) (mindspore_rl.agent.Agent method) get_item() (mindspore_rl.core.ReplayBuffer method) get_replay_buffer() (mindspore_rl.core.MSRL method)

get_replay_buffer_elements() (mindspore_rl.core.MSRL method) get_step_info() (mindspore_rl.environment.StarCraft2Environment 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.ReplayBuffer 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)

M

max_utility() (mindspore_rl.environment.TicTacToeEnvironment method) mindspore_rl module mindspore_rl.agent module mindspore_rl.core module mindspore_rl.environment module mindspore_rl.network module mindspore_rl.policy module

module mindspore_rl mindspore_rl.agent mindspore_rl.core mindspore_rl.environment mindspore_rl.network mindspore_rl.policy 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_values (mindspore_rl.environment.Space property)

O

observation_space (mindspore_rl.environment.Environment property) (mindspore_rl.environment.GymEnvironment property) (mindspore_rl.environment.MsEnvironment property) (mindspore_rl.environment.MultiEnvironmentWrapper property) (mindspore_rl.environment.StarCraft2Environment property) (mindspore_rl.environment.TicTacToeEnvironment property)

P

Policy (class in mindspore_rl.policy)

PriorityReplayBuffer (class in mindspore_rl.core) push() (mindspore_rl.core.PriorityReplayBuffer method)

R

RandomPolicy (class in mindspore_rl.policy) ReplayBuffer (class in mindspore_rl.core) reset() (mindspore_rl.core.ReplayBuffer method) (mindspore_rl.environment.Environment method) (mindspore_rl.environment.GymEnvironment method) (mindspore_rl.environment.MsEnvironment method) (mindspore_rl.environment.MultiEnvironmentWrapper method) (mindspore_rl.environment.StarCraft2Environment method) (mindspore_rl.environment.TicTacToeEnvironment method)

reward_space (mindspore_rl.environment.Environment property) (mindspore_rl.environment.GymEnvironment property) (mindspore_rl.environment.MsEnvironment property) (mindspore_rl.environment.MultiEnvironmentWrapper property) (mindspore_rl.environment.StarCraft2Environment 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.ReplayBuffer method) (mindspore_rl.environment.Space method) save() (mindspore_rl.environment.TicTacToeEnvironment method) Session (class in mindspore_rl.core) shape (mindspore_rl.environment.Space property) size() (mindspore_rl.core.ReplayBuffer method)

Space (class in mindspore_rl.environment) StarCraft2Environment (class in mindspore_rl.environment) step() (mindspore_rl.environment.Environment method) (mindspore_rl.environment.GymEnvironment method) (mindspore_rl.environment.MsEnvironment method) (mindspore_rl.environment.MultiEnvironmentWrapper method) (mindspore_rl.environment.StarCraft2Environment method) (mindspore_rl.environment.TicTacToeEnvironment method)

T

TicTacToeEnvironment (class in mindspore_rl.environment) 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

update_priorities() (mindspore_rl.core.PriorityReplayBuffer method)