Class WaterballRLEnvironment

Waterball environment

Hierarchy (View Summary)

RLEnvironmentBase
- WaterballRLEnvironment

Constructors

constructor

new WaterballRLEnvironment(
width: number,
height: number,
): WaterballRLEnvironment
Parameters
- width: number
  Area width
- height: number
  Area height
Returns WaterballRLEnvironment
Overrides RLEnvironmentBase.constructor
- Defined in lib/rl/waterball.d.ts:9

Properties

__state

__state: any

__states

__states: RLRealRange[]

_agent_max_velocity

_agent_max_velocity: number

_agent_p

_agent_p: number[]

_agent_radius

_agent_radius: number

_agent_v

_agent_v: number[]

_agent_velocity_step

_agent_velocity_step: number

_ball_max_velocity

_ball_max_velocity: number

_ball_min_velocity

_ball_min_velocity: number

_ball_radius

_ball_radius: number

_balls

_balls: any[]

_cos

_cos: number[]

_epoch

_epoch: number

_height

_height: number

_history_state

_history_state: any[]

_history_state_size

_history_state_size: number

_max_position

_max_position: number[]

_max_size

_max_size: number

_min_position

_min_position: number[]

_sensor_count

_sensor_count: number

_sensor_length

_sensor_length: number

_sin

_sin: number[]

_width

_width: number

Accessors

actions

get actions(): number[][]
Returns number[][]
- Defined in lib/rl/waterball.d.ts:30

current_state

get current_state(): any[]
Returns any[]
- Defined in lib/rl/waterball.d.ts:33

epoch

get epoch(): number
Epoch

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

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(): RLRealRange[]
Returns RLRealRange[]
- Defined in lib/rl/waterball.d.ts:31

Methods

addBall

addBall(): void
Returns void
- Defined in lib/rl/waterball.d.ts:34

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/waterball.d.ts:35

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
Inherited from RLEnvironmentBase.setState
- Defined in lib/rl/base.d.ts:99

state

state(): any
Returns current state.

Returns any
Current state
Overrides RLEnvironmentBase.state
- Defined in lib/rl/waterball.d.ts:36

step

step(action: any): { done: boolean; reward: number; state: any }
Do action and returns new state.
Parameters
- action: any
  Actions to be performed by the agent
Returns { done: boolean; reward: number; state: any }
state, reward, done
Overrides RLEnvironmentBase.step
- Defined in lib/rl/waterball.d.ts:38

test

test(
    state: any[],
    action: any[],
    agent: any,
): { done: boolean; invalid?: boolean; 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[] }
state, reward, done
Inherited from RLEnvironmentBase.test
- Defined in lib/rl/base.d.ts:119

Class WaterballRLEnvironment

Hierarchy (View Summary)

Index

Constructors

Properties

Accessors

Methods

Constructors

constructor

Parameters

Returns WaterballRLEnvironment

Properties

__state

__states

_agent_max_velocity

_agent_p

_agent_radius

_agent_v

_agent_velocity_step

_ball_max_velocity

_ball_min_velocity

_ball_radius

_balls

_cos

_epoch

_height

_history_state

_history_state_size

_max_position

_max_size

_min_position

_sensor_count

_sensor_length

_sin

_width

Accessors

actions

Returns number[][]

current_state

Returns any[]

epoch

Returns number

reward

Parameters

Returns void

states

Returns RLRealRange[]

Methods

addBall

Returns void

clone

Returns RLEnvironmentBase

reset

Returns any

sample_action

Parameters

Returns any[]

setState

Parameters

Returns void

state

Returns any

step

Parameters

Returns { done: boolean; reward: number; state: any }

test

Parameters

Returns { done: boolean; invalid?: boolean; reward: number; state: any[] }

Settings

On This Page