2016-04-27 08:00:58 -07:00
|
|
|
"""
|
|
|
|
Task is to reverse content over the input tape.
|
|
|
|
http://arxiv.org/abs/1511.07275
|
|
|
|
"""
|
|
|
|
|
|
|
|
import numpy as np
|
|
|
|
from gym.envs.algorithmic import algorithmic_env
|
|
|
|
|
2016-10-21 16:06:48 -07:00
|
|
|
class ReverseEnv(algorithmic_env.TapeAlgorithmicEnv):
|
|
|
|
MIN_REWARD_SHORTFALL_FOR_PROMOTION = -.1
|
2016-04-27 08:00:58 -07:00
|
|
|
def __init__(self, base=2):
|
2016-10-21 16:06:48 -07:00
|
|
|
super(ReverseEnv, self).__init__(base=base, chars=True, starting_min_length=1)
|
2016-04-27 08:00:58 -07:00
|
|
|
self.last = 50
|
|
|
|
|
2016-10-21 16:06:48 -07:00
|
|
|
def target_from_input_data(self, input_str):
|
|
|
|
return list(reversed(input_str))
|