quynhtrangdao / env Goto Github PK

from setup import make
from numba import njit, jit
import numpy as np

@njit()
def Agent(state, perData):
    validActions = env.getValidActions(state)
    actions = np.where(validActions==1)[0]
    action = np.random.choice(actions)
    return arr_action[idx], perData

perData = np.array([0])
level = 0
count_game_train = 1000
count_win, perData = env.numba_main_2(Agent, count_game_train, perData, level)
print(count_win)

* Agent(state, perData):
    input: state, data
    output: action(int), data
* getValidActions(state): 
    input: state(np.float64)
    output: np.array valid action in turn of Environment
* getReward(state):
    input: state(np.float64)
    output: -1, 0, 1
* getActionSize():
    input: None
    output: int, count of array action size of Env
* getStateSize():
    input: None
    output: int, count of array state size of Env

from CheckEnv import check_env
import your_env as env #path to your env
print(check_env(env))

from CheckPlayer import check_player
import your_agent as agent #path to your env
print(check_player(env))