thu-ml · Trinkle23897 · Mar 13, 2023 · Mar 13, 2023 · Mar 13, 2023 · Mar 13, 2023
diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md
@@ -7,6 +7,6 @@
 - [ ] I have searched through the [issue tracker](https://github.com/thu-ml/tianshou/issues) for duplicates
 - [ ] I have mentioned version numbers, operating system and environment, where applicable:
   ```python
-  import tianshou, gym, torch, numpy, sys
+  import tianshou, gymnasium as gym, torch, numpy, sys
   print(tianshou.__version__, gym.__version__, torch.__version__, numpy.__version__, sys.version, sys.platform)
   ```
diff --git a/.github/workflows/extra_sys.yml b/.github/workflows/extra_sys.yml
@@ -12,12 +12,12 @@ jobs:
         python-version: [3.7, 3.8]
     steps:
       - name: Cancel previous run
-        uses: styfle/cancel-workflow-action@0.9.1
+        uses: styfle/cancel-workflow-action@0.11.0
         with:
           access_token: ${{ github.token }}
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
       - name: Upgrade pip

diff --git a/.github/workflows/gputest.yml b/.github/workflows/gputest.yml
@@ -8,12 +8,12 @@ jobs:
     if: "!contains(github.event.head_commit.message, 'ci skip')"
     steps:
       - name: Cancel previous run
-        uses: styfle/cancel-workflow-action@0.9.1
+        uses: styfle/cancel-workflow-action@0.11.0
         with:
           access_token: ${{ github.token }}
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Set up Python 3.8
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: 3.8
       - name: Upgrade pip

diff --git a/.github/workflows/lint_and_docs.yml b/.github/workflows/lint_and_docs.yml
@@ -7,12 +7,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Cancel previous run
-        uses: styfle/cancel-workflow-action@0.9.1
+        uses: styfle/cancel-workflow-action@0.11.0
         with:
           access_token: ${{ github.token }}
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Set up Python 3.8
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: 3.8
       - name: Upgrade pip

diff --git a/.github/workflows/profile.yml b/.github/workflows/profile.yml
diff --git a/.github/workflows/pytest.yml b/.github/workflows/pytest.yml
@@ -11,12 +11,12 @@ jobs:
         python-version: [3.7, 3.8, 3.9]
     steps:
       - name: Cancel previous run
-        uses: styfle/cancel-workflow-action@0.9.1
+        uses: styfle/cancel-workflow-action@0.11.0
         with:
           access_token: ${{ github.token }}
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
       - name: Upgrade pip

diff --git a/docs/requirements.txt b/docs/requirements.txt
@@ -1,10 +1,10 @@
 gym
 numba
 numpy>=1.20
-sphinx<4
+sphinx
 sphinxcontrib-bibtex
 tensorboard
 torch
 tqdm
-protobuf~=3.19.0
+protobuf
 pettingzoo
diff --git a/test/offline/test_discrete_bcq.py b/test/offline/test_discrete_bcq.py
@@ -40,7 +40,7 @@ def get_args():
     parser.add_argument("--hidden-sizes", type=int, nargs="*", default=[64, 64])
     parser.add_argument("--test-num", type=int, default=100)
     parser.add_argument("--logdir", type=str, default="log")
-    parser.add_argument("--render", type=float, default=0.)
+    parser.add_argument("--render", type=float, default=0.0)
     parser.add_argument("--load-buffer-name", type=str, default=expert_file_name())
     parser.add_argument(
         "--device",
@@ -59,7 +59,7 @@ def test_discrete_bcq(args=get_args()):
     args.state_shape = env.observation_space.shape or env.observation_space.n
     args.action_shape = env.action_space.shape or env.action_space.n
     if args.reward_threshold is None:
-        default_reward_threshold = {"CartPole-v0": 190}
+        default_reward_threshold = {"CartPole-v0": 185}
         args.reward_threshold = default_reward_threshold.get(
             args.task, env.spec.reward_threshold
         )
@@ -123,7 +123,8 @@ def save_checkpoint_fn(epoch, env_step, gradient_step):
             {
                 "model": policy.state_dict(),
                 "optim": optim.state_dict(),
-            }, ckpt_path
+            },
+            ckpt_path,
         )
         return ckpt_path
 

diff --git a/tianshou/__init__.py b/tianshou/__init__.py
@@ -1,6 +1,6 @@
 from tianshou import data, env, exploration, policy, trainer, utils
 
-__version__ = "0.4.11"
+__version__ = "0.5.0"
 
 __all__ = [
     "env",

diff --git a/tianshou/env/venvs.py b/tianshou/env/venvs.py
@@ -5,7 +5,6 @@
 import numpy as np
 import packaging
 
-from tianshou.env.pettingzoo_env import PettingZooEnv
 from tianshou.env.utils import ENV_TYPE, gym_new_venv_step_type
 from tianshou.env.worker import (
     DummyEnvWorker,
@@ -14,8 +13,14 @@
     SubprocEnvWorker,
 )
 
+try:
+    from tianshou.env.pettingzoo_env import PettingZooEnv
+except ImportError:
+    PettingZooEnv = None  # type: ignore
+
 try:
     import gym as old_gym
+
     has_old_gym = True
 except ImportError:
     has_old_gym = False
@@ -152,11 +157,13 @@ def __init__(
 
         self.env_num = len(env_fns)
         self.wait_num = wait_num or len(env_fns)
-        assert 1 <= self.wait_num <= len(env_fns), \
-            f"wait_num should be in [1, {len(env_fns)}], but got {wait_num}"
+        assert (
+            1 <= self.wait_num <= len(env_fns)
+        ), f"wait_num should be in [1, {len(env_fns)}], but got {wait_num}"
         self.timeout = timeout
-        assert self.timeout is None or self.timeout > 0, \
-            f"timeout is {timeout}, it should be positive if provided!"
+        assert (
+            self.timeout is None or self.timeout > 0
+        ), f"timeout is {timeout}, it should be positive if provided!"
         self.is_async = self.wait_num != len(env_fns) or timeout is not None
         self.waiting_conn: List[EnvWorker] = []
         # environments in self.ready_id is actually ready
@@ -169,8 +176,9 @@ def __init__(
         self.is_closed = False
 
     def _assert_is_not_closed(self) -> None:
-        assert not self.is_closed, \
-            f"Methods of {self.__class__.__name__} cannot be called after close."
+        assert (
+            not self.is_closed
+        ), f"Methods of {self.__class__.__name__} cannot be called after close."
 
     def __len__(self) -> int:
         """Return len(self), which is the number of environments."""
@@ -245,10 +253,12 @@ def _wrap_id(
 
     def _assert_id(self, id: Union[List[int], np.ndarray]) -> None:
         for i in id:
-            assert i not in self.waiting_id, \
-                f"Cannot interact with environment {i} which is stepping now."
-            assert i in self.ready_id, \
-                f"Can only interact with ready environments {self.ready_id}."
+            assert (
+                i not in self.waiting_id
+            ), f"Cannot interact with environment {i} which is stepping now."
+            assert (
+                i in self.ready_id
+            ), f"Can only interact with ready environments {self.ready_id}."
 
     def reset(
         self,
@@ -271,9 +281,10 @@ def reset(
             self.workers[i].send(None, **kwargs)
         ret_list = [self.workers[i].recv() for i in id]
 
-        assert isinstance(ret_list[0], (tuple, list)) and len(
-            ret_list[0]
-        ) == 2 and isinstance(ret_list[0][1], dict)
+        assert (
+            isinstance(ret_list[0], (tuple, list)) and len(ret_list[0]) == 2
+            and isinstance(ret_list[0][1], dict)
+        )
 
         obs_list = [r[0] for r in ret_list]
 
@@ -367,9 +378,13 @@ def step(
             obs_stack = np.stack(obs_list)
         except ValueError:  # different len(obs)
             obs_stack = np.array(obs_list, dtype=object)
-        return obs_stack, np.stack(rew_list), np.stack(term_list), np.stack(
-            trunc_list
-        ), np.stack(info_list)
+        return (
+            obs_stack,
+            np.stack(rew_list),
+            np.stack(term_list),
+            np.stack(trunc_list),
+            np.stack(info_list),
+        )
 
     def seed(
         self,