File size: 1,054 Bytes
5960497 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 | import numpy as np
from gym import Env
from gym.spaces import Discrete
class FixedSequenceEnv(Env):
def __init__(
self,
n_actions=10,
episode_len=100
):
self.action_space = Discrete(n_actions)
self.observation_space = Discrete(1)
self.np_random = np.random.RandomState(0)
self.episode_len = episode_len
self.sequence = [self.np_random.randint(0, self.action_space.n)
for _ in range(self.episode_len)]
self.time = 0
def reset(self):
self.time = 0
return 0
def step(self, actions):
rew = self._get_reward(actions)
self._choose_next_state()
done = False
if self.episode_len and self.time >= self.episode_len:
done = True
return 0, rew, done, {}
def seed(self, seed=None):
self.np_random.seed(seed)
def _choose_next_state(self):
self.time += 1
def _get_reward(self, actions):
return 1 if actions == self.sequence[self.time] else 0
|