mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-05-18 21:30:19 +00:00
* add vectorized monitor * auto format of the code * add documentation and VecExtractDictObs * refactor and add test cases * add test cases and format * avoid circular import and fix doc * fix type * fix type * oops * Update stable_baselines3/common/monitor.py Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org> * Update stable_baselines3/common/monitor.py Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org> * add test cases * update changelog * fix mutable argument * quick fix * Apply suggestions from code review * fix terminal observation for gym3 envs * delete comment * Update doc and bump version * Add warning when already using `Monitor` wrapper * Update vecmonitor tests * Fixes Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
24 lines
755 B
Python
24 lines
755 B
Python
import numpy as np
|
|
|
|
from stable_baselines3.common.vec_env.base_vec_env import VecEnv, VecEnvStepReturn, VecEnvWrapper
|
|
|
|
|
|
class VecExtractDictObs(VecEnvWrapper):
|
|
"""
|
|
A vectorized wrapper for extracting dictionary observations.
|
|
|
|
:param venv: The vectorized environment
|
|
:param key: The key of the dictionary observation
|
|
"""
|
|
|
|
def __init__(self, venv: VecEnv, key: str):
|
|
self.key = key
|
|
super().__init__(venv=venv, observation_space=venv.observation_space.spaces[self.key])
|
|
|
|
def reset(self) -> np.ndarray:
|
|
obs = self.venv.reset()
|
|
return obs[self.key]
|
|
|
|
def step_wait(self) -> VecEnvStepReturn:
|
|
obs, reward, done, info = self.venv.step_wait()
|
|
return obs[self.key], reward, done, info
|