6c6c872523
Changes: - Disclaimer in README - Replaced all occurences of Gym with Gymnasium - Removed code that is now dead since we no longer need to support the old step API - Updated type hints to only allow new step API - Increased required version of envpool to support Gymnasium - Increased required version of PettingZoo to support Gymnasium - Updated `PettingZooEnv` to only use the new step API, removed hack to also support old API - I had to add some `# type: ignore` comments, due to new type hinting in Gymnasium. I'm not that familiar with type hinting but I believe that the issue is on the Gymnasium side and we are looking into it. - Had to update `MyTestEnv` to support `options` kwarg - Skip NNI tests because they still use OpenAI Gym - Also allow `PettingZooEnv` in vector environment - Updated doc page about ReplayBuffer to also talk about terminated and truncated flags. Still need to do: - Update the Jupyter notebooks in docs - Check the entire code base for more dead code (from compatibility stuff) - Check the reset functions of all environments/wrappers in code base to make sure they use the `options` kwarg - Someone might want to check test_env_finite.py - Is it okay to allow `PettingZooEnv` in vector environments? Might need to update docs?
53 lines
1.6 KiB
Python
53 lines
1.6 KiB
Python
from typing import Any, Callable, List, Optional, Tuple
|
|
|
|
import gymnasium as gym
|
|
import numpy as np
|
|
|
|
from tianshou.env.worker import EnvWorker
|
|
|
|
|
|
class DummyEnvWorker(EnvWorker):
|
|
"""Dummy worker used in sequential vector environments."""
|
|
|
|
def __init__(self, env_fn: Callable[[], gym.Env]) -> None:
|
|
self.env = env_fn()
|
|
super().__init__(env_fn)
|
|
|
|
def get_env_attr(self, key: str) -> Any:
|
|
return getattr(self.env, key)
|
|
|
|
def set_env_attr(self, key: str, value: Any) -> None:
|
|
setattr(self.env.unwrapped, key, value)
|
|
|
|
def reset(self, **kwargs: Any) -> Tuple[np.ndarray, dict]:
|
|
if "seed" in kwargs:
|
|
super().seed(kwargs["seed"])
|
|
return self.env.reset(**kwargs)
|
|
|
|
@staticmethod
|
|
def wait( # type: ignore
|
|
workers: List["DummyEnvWorker"], wait_num: int, timeout: Optional[float] = None
|
|
) -> List["DummyEnvWorker"]:
|
|
# Sequential EnvWorker objects are always ready
|
|
return workers
|
|
|
|
def send(self, action: Optional[np.ndarray], **kwargs: Any) -> None:
|
|
if action is None:
|
|
self.result = self.env.reset(**kwargs)
|
|
else:
|
|
self.result = self.env.step(action) # type: ignore
|
|
|
|
def seed(self, seed: Optional[int] = None) -> Optional[List[int]]:
|
|
super().seed(seed)
|
|
try:
|
|
return self.env.seed(seed) # type: ignore
|
|
except (AttributeError, NotImplementedError):
|
|
self.env.reset(seed=seed)
|
|
return [seed] # type: ignore
|
|
|
|
def render(self, **kwargs: Any) -> Any:
|
|
return self.env.render(**kwargs)
|
|
|
|
def close_env(self) -> None:
|
|
self.env.close()
|