Class SARSAAgent

constructor

• new SARSAAgent(env: RLEnvironmentBase, resolution?: number): SARSAAgent

• Parameters

  • env: RLEnvironmentBase

    Environment
  • Optionalresolution: number

    Resolution

  Returns SARSAAgent

_env

_last_action

_last_reward

_last_state

_table

get_action

• get_action(state: any[], greedy_rate?: number): any[]

• Returns a action.

  Parameters

  • state: any[]

    Current states
  • Optionalgreedy_rate: number

    Greedy rate

  Returns any[]

  Action

get_score

• get_score(): number[][][]

• Returns a score.

  Returns number[][][]

  Score values

reset

• reset(): void

• Reset agent.

  Returns void

update

• update(action: any[], state: any[], next_state: any[], reward: number): void

• Update model.

  Parameters

  • action: any[]

    Action
  • state: any[]

    Current states
  • next_state: any[]

    Next states
  • reward: number

    Reward

  Returns void