mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-23 23:12:46 +00:00
58e6aa95e5
* 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
28 lines
1.0 KiB
Python
28 lines
1.0 KiB
Python
import numpy as np
|
|
from gym.envs.algorithmic import algorithmic_env
|
|
from gym.envs.algorithmic.algorithmic_env import ha
|
|
|
|
class ReversedAdditionEnv(algorithmic_env.AlgorithmicEnv):
|
|
def __init__(self, rows=2, base=3):
|
|
self.rows = rows
|
|
algorithmic_env.AlgorithmicEnv.__init__(self,
|
|
inp_dim=2,
|
|
base=base,
|
|
chars=False)
|
|
def set_data(self):
|
|
self.content = {}
|
|
self.target = {}
|
|
curry = 0
|
|
for i in range(self.total_len):
|
|
vals = []
|
|
for k in range(self.rows):
|
|
val = self.np_random.randint(self.base)
|
|
self.content[ha(np.array([i, k]))] = val
|
|
vals.append(val)
|
|
total = sum(vals) + curry
|
|
self.target[i] = total % self.base
|
|
curry = total / self.base
|
|
if curry > 0:
|
|
self.target[self.total_len] = curry
|
|
self.total_reward = self.total_len
|