Fixed awarding and penalty at the end of each game
This commit is contained in:
@@ -1,6 +1,12 @@
|
||||
import enum
|
||||
|
||||
import numpy as np
|
||||
from numpy.random import uniform
|
||||
|
||||
class Reason(enum.Enum):
|
||||
Won = 1
|
||||
Lost = 2
|
||||
Undecided = 3
|
||||
|
||||
class APlayer(object):
|
||||
def __init__(self, mark):
|
||||
@@ -15,6 +21,9 @@ class APlayer(object):
|
||||
def move(self, state: np.array):
|
||||
return state, False
|
||||
|
||||
def reward(self, value):
|
||||
pass
|
||||
|
||||
def new_game(self):
|
||||
pass
|
||||
|
||||
|
||||
Reference in New Issue
Block a user