mirror of
https://github.com/vale981/ray
synced 2025-03-06 18:41:40 -05:00
36 lines
1.1 KiB
Python
36 lines
1.1 KiB
Python
|
import gym
|
||
|
|
from gym.spaces import Box, Discrete
|
||
|
|
import numpy as np
|
||
|
|
|
||
|
|
|
||
|
|
class SimpleCorridor(gym.Env):
|
||
|
|
"""Example of a custom env in which you have to walk down a corridor.
|
||
|
|
|
||
|
|
You can configure the length of the corridor via the env config."""
|
||
|
|
|
||
|
|
def __init__(self, config):
|
||
|
|
self.end_pos = config["corridor_length"]
|
||
|
|
self.cur_pos = 0
|
||
|
|
self.action_space = Discrete(2)
|
||
|
|
self.observation_space = Box(
|
||
|
|
0.0, self.end_pos, shape=(1, ), dtype=np.float32)
|
||
|
|
|
||
|
|
def set_corridor_length(self, length):
|
||
|
|
self.end_pos = length
|
||
|
|
self.observation_space = Box(
|
||
|
|
0.0, self.end_pos, shape=(1, ), dtype=np.float32)
|
||
|
|
print("Updated corridor length to {}".format(length))
|
||
|
|
|
||
|
|
def reset(self):
|
||
|
|
self.cur_pos = 0
|
||
|
|
return [self.cur_pos]
|
||
|
|
|
||
|
|
def step(self, action):
|
||
|
|
assert action in [0, 1], action
|
||
|
|
if action == 0 and self.cur_pos > 0:
|
||
|
|
self.cur_pos -= 1
|
||
|
|
elif action == 1:
|
||
|
|
self.cur_pos += 1
|
||
|
|
done = self.cur_pos >= self.end_pos
|
||
|
|
return [self.cur_pos], 1 if done else 0, done, {}
|