21 lines
540 B
Python
21 lines
540 B
Python
|
import random, collections
|
||
|
|
StepOutput = collections.namedtuple("step_output", ["action", "probs"])
|
||
|
|
|
||
|
|
|
||
|
|
class Agent(object):
|
||
|
|
def __init__(self):
|
||
|
|
pass
|
||
|
|
|
||
|
|
def step(self, timestep):
|
||
|
|
raise NotImplementedError
|
||
|
|
|
||
|
|
|
||
|
|
class RandomAgent(Agent):
|
||
|
|
def __init__(self, _id):
|
||
|
|
super().__init__()
|
||
|
|
self.player_id = _id
|
||
|
|
|
||
|
|
def step(self, timestep):
|
||
|
|
cur_player = timestep.observations["current_player"]
|
||
|
|
return StepOutput(action=random.choice(timestep.observations["legal_actions"][cur_player]), probs=1.0)
|