Constructors
Properties
_env
_history
_history: any[]
_table
_table: MCTable
Methods
get_action
- get_action(state: any[], greedy_rate?: number): any[]
Parameters
- state: any[]
Optional
greedy_rate: number
Returns any[]
Action
get_score
- get_score(): number[][][]
Returns number[][][]
Score values
reset
- reset(): void
Returns void
update
- update(action: any[], state: any[], reward: number, done: boolean): void
Parameters
- action: any[]
- state: any[]
- reward: number
- done: boolean
Returns void
Monte Carlo agent