mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-01 22:11:25 +00:00
bf093c6890
* Remove additional ignores from flake8 * Remove all unused imports * Remove all unused imports * Update flake8 and pyupgrade * F841, removed unused variables * E731, removed lambda assignment to variables * Remove E731, F403, F405, F524 * Remove E722, bare exceptions * Remove E712, compare variable == True or == False to is True or is False * Remove E402, module level import not at top of file * Added --pre-file-ignores * Add --per-file-ignores removing E741, E302 and E704 * Add E741, do not use variables named ‘l’, ‘O’, or ‘I’ to ignore issues in classic control * Fixed issues for pytest==6.2 * Remove unnecessary # noqa * Edit comment with the removal of E302 * Added warnings and declared module, attr for pyright type hinting * Remove unused import * Removed flake8 E302 * Updated flake8 from 3.9.2 to 4.0.1 * Remove unused variable
60 lines
2.1 KiB
Python
60 lines
2.1 KiB
Python
import time
|
|
from collections import deque
|
|
|
|
import numpy as np
|
|
|
|
import gym
|
|
|
|
|
|
class RecordEpisodeStatistics(gym.Wrapper):
|
|
def __init__(self, env, deque_size=100):
|
|
super().__init__(env)
|
|
self.num_envs = getattr(env, "num_envs", 1)
|
|
self.t0 = time.perf_counter()
|
|
self.episode_count = 0
|
|
self.episode_returns = None
|
|
self.episode_lengths = None
|
|
self.return_queue = deque(maxlen=deque_size)
|
|
self.length_queue = deque(maxlen=deque_size)
|
|
self.is_vector_env = getattr(env, "is_vector_env", False)
|
|
|
|
def reset(self, **kwargs):
|
|
observations = super().reset(**kwargs)
|
|
self.episode_returns = np.zeros(self.num_envs, dtype=np.float32)
|
|
self.episode_lengths = np.zeros(self.num_envs, dtype=np.int32)
|
|
return observations
|
|
|
|
def step(self, action):
|
|
observations, rewards, dones, infos = super().step(action)
|
|
self.episode_returns += rewards
|
|
self.episode_lengths += 1
|
|
if not self.is_vector_env:
|
|
infos = [infos]
|
|
dones = [dones]
|
|
else:
|
|
infos = list(infos) # Convert infos to mutable type
|
|
for i in range(len(dones)):
|
|
if dones[i]:
|
|
infos[i] = infos[i].copy()
|
|
episode_return = self.episode_returns[i]
|
|
episode_length = self.episode_lengths[i]
|
|
episode_info = {
|
|
"r": episode_return,
|
|
"l": episode_length,
|
|
"t": round(time.perf_counter() - self.t0, 6),
|
|
}
|
|
infos[i]["episode"] = episode_info
|
|
self.return_queue.append(episode_return)
|
|
self.length_queue.append(episode_length)
|
|
self.episode_count += 1
|
|
self.episode_returns[i] = 0
|
|
self.episode_lengths[i] = 0
|
|
if self.is_vector_env:
|
|
infos = tuple(infos)
|
|
return (
|
|
observations,
|
|
rewards,
|
|
dones if self.is_vector_env else dones[0],
|
|
infos if self.is_vector_env else infos[0],
|
|
)
|