Files
Gymnasium/gym/envs/algorithmic/reverse.py

27 lines
926 B
Python
Raw Normal View History

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
from gym.envs.algorithmic.algorithmic_env import ha
class ReverseEnv(algorithmic_env.AlgorithmicEnv):
def __init__(self, base=2):
algorithmic_env.AlgorithmicEnv.__init__(self,
inp_dim=1,
base=base,
chars=True)
algorithmic_env.AlgorithmicEnv.current_length = 1
self.last = 50
def set_data(self):
self.content = {}
self.target = {}
for i in range(self.total_len):
[WIP] add support for seeding environments (#135) * Make environments seedable * Fix monitor bugs - Set monitor_id before setting the infix. This was a bug that would yield incorrect results with multiple monitors. - Remove extra pid from stats recorder filename. This should be purely cosmetic. * Start uploading seeds in episode_batch * Fix _bigint_from_bytes for python3 * Set seed explicitly in random_agent * Pass through seed argument * Also pass through random state to spaces * Pass random state into the observation/action spaces * Make all _seed methods return the list of used seeds * Switch over to np.random where possible * Start hashing seeds, and also seed doom engine * Fixup seeding determinism in many cases * Seed before loading the ROM * Make seeding more Python3 friendly * Make the MuJoCo skipping a bit more forgiving * Remove debugging PDB calls * Make setInt argument into raw bytes * Validate and upload seeds * Skip box2d * Make seeds smaller, and change representation of seeds in upload * Handle long seeds * Fix RandomAgent example to be deterministic * Handle integer types correctly in Python2 and Python3 * Try caching pip * Try adding swap * Add df and free calls * Bump swap * Bump swap size * Try setting overcommit * Try other sysctls * Try fixing overcommit * Try just setting overcommit_memory=1 * Add explanatory comment * Add what's new section to readme * BUG: Mark ElevatorAction-ram-v0 as non-deterministic for now * Document seed * Move nondetermistic check into spec
2016-05-29 09:07:09 -07:00
val = self.np_random.randint(self.base)
2016-04-27 08:00:58 -07:00
self.content[ha(np.array([i]))] = val
self.target[self.total_len - i - 1] = val
self.total_reward = self.total_len + 0.9