Class ReversiRLEnvironment

Reversi environment

Hierarchy (View Summary)

RLEnvironmentBase
- ReversiRLEnvironment

Index

Constructors

Properties

_agents _board _epoch _evaluation _reward _size _turn BLACK EMPTY OTHER OWN WHITE

Accessors

actions epoch evaluation reward states

Methods

_checkAgent _makeState _state2board clone reset sample_action setState state step test

Constructors

constructor

new ReversiRLEnvironment(): ReversiRLEnvironment
Returns ReversiRLEnvironment
Inherited from RLEnvironmentBase.constructor

Properties

_agents

_agents: number[]

_board

_board: ReversiBoard

_epoch

_epoch: number

_evaluation

_evaluation: (board: any, turn: any) => any

_reward

_reward: { lose: number; step: number; win: number }

_size

_size: number[]

_turn

_turn: number

`Static`BLACK

BLACK: number

`Static`EMPTY

EMPTY: number

`Static`OTHER

OTHER: number

`Static`OWN

OWN: number

`Static`WHITE

WHITE: number

Accessors

actions

get actions(): number[][]
Returns number[][]
- Defined in lib/rl/reversi.d.ts:18

epoch

get epoch(): number
Epoch

Returns number
Inherited from RLEnvironmentBase.epoch
- Defined in lib/rl/base.d.ts:73

evaluation

set evaluation(func: any): void
Parameters
- func: any
Returns void
- Defined in lib/rl/reversi.d.ts:20

reward

set reward(value: object): void
Reward
Parameters
- value: object
  Reward object
Returns void
Inherited from RLEnvironmentBase.reward
- Defined in lib/rl/base.d.ts:78

states

get states(): number[][]
Returns number[][]
- Defined in lib/rl/reversi.d.ts:19

Methods

_checkAgent

_checkAgent(agent: any): void
Parameters
- agent: any
Returns void
- Defined in lib/rl/reversi.d.ts:24

_makeState

_makeState(board: any, agentturn: any, gameturn: any): any[]
Parameters
- board: any
- agentturn: any
- gameturn: any
Returns any[]
- Defined in lib/rl/reversi.d.ts:22

_state2board

_state2board(state: any, turn: any): ReversiBoard
Parameters
- state: any
- turn: any
Returns ReversiBoard
- Defined in lib/rl/reversi.d.ts:23

clone

clone(): RLEnvironmentBase
Returns cloned environment.

Returns RLEnvironmentBase
Cloned environment
Inherited from RLEnvironmentBase.clone
- Defined in lib/rl/base.d.ts:83

reset

reset(): any[]
Reset environment.

Returns any[]
Overrides RLEnvironmentBase.reset
- Defined in lib/rl/reversi.d.ts:25

sample_action

sample_action(agent: any): any[]
Sample an action.
Parameters
- agent: any
  Agent
Returns any[]
Sampled action
Inherited from RLEnvironmentBase.sample_action
- Defined in lib/rl/base.d.ts:130

setState

setState(state: any, agent: any): void
Set new state.
Parameters
- state: any
  New state
- agent: any
  Agent
Returns void
Overrides RLEnvironmentBase.setState
- Defined in lib/rl/reversi.d.ts:28

state

state(agent: any): any[]
Returns current state.
Parameters
- agent: any
  Agent
Returns any[]
Current state
Overrides RLEnvironmentBase.state
- Defined in lib/rl/reversi.d.ts:27

step

step(
action: any,
agent: any,
): { done: boolean; invalid?: boolean; reward: number; state: any[] }
Do action and returns new state.
Parameters
- action: any
  Actions to be performed by the agent
- agent: any
  Agent
Returns { done: boolean; invalid?: boolean; reward: number; state: any[] }
state, reward, done
Overrides RLEnvironmentBase.step
- Defined in lib/rl/reversi.d.ts:29

test

test(
    state: any,
    action: any,
    agent: any,
):
    | { done: boolean; invalid: boolean; reward: number; state: any }
    | { done: boolean; invalid?: undefined; reward: number; state: any[] }
Do actioin without changing environment and returns new state.
Parameters
- state: any
  Environment state
- action: any
  Actions to be performed by the agent
- agent: any
  Agent
Returns
| { done: boolean; invalid: boolean; reward: number; state: any }
| { done: boolean; invalid?: undefined; reward: number; state: any[] }
state, reward, done
Overrides RLEnvironmentBase.test
- Defined in lib/rl/reversi.d.ts:35