thu-ml · Trinkle23897 · Jul 4, 2022 · Jul 4, 2022 · Jul 4, 2022
diff --git a/.github/workflows/extra_sys.yml b/.github/workflows/extra_sys.yml
@@ -11,6 +11,10 @@ jobs:
         os: [macos-latest, windows-latest]
         python-version: [3.7, 3.8]
     steps:
+    - name: Cancel previous run
+      uses: styfle/cancel-workflow-action@0.9.1
+      with:
+        access_token: ${{ github.token }}
     - uses: actions/checkout@v2
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v2

diff --git a/.github/workflows/gputest.yml b/.github/workflows/gputest.yml
@@ -7,6 +7,10 @@ jobs:
     runs-on: [self-hosted, Linux, X64]
     if: "!contains(github.event.head_commit.message, 'ci skip')"
     steps:
+    - name: Cancel previous run
+      uses: styfle/cancel-workflow-action@0.9.1
+      with:
+        access_token: ${{ github.token }}
     - uses: actions/checkout@v2
     - name: Set up Python 3.8
       uses: actions/setup-python@v2

diff --git a/.github/workflows/lint_and_docs.yml b/.github/workflows/lint_and_docs.yml
@@ -6,6 +6,10 @@ jobs:
   check:
     runs-on: ubuntu-latest
     steps:
+    - name: Cancel previous run
+      uses: styfle/cancel-workflow-action@0.9.1
+      with:
+        access_token: ${{ github.token }}
     - uses: actions/checkout@v2
     - name: Set up Python 3.8
       uses: actions/setup-python@v2

diff --git a/.github/workflows/profile.yml b/.github/workflows/profile.yml
@@ -7,6 +7,10 @@ jobs:
     runs-on: ubuntu-latest
     if: "!contains(github.event.head_commit.message, 'ci skip')"
     steps:
+    - name: Cancel previous run
+      uses: styfle/cancel-workflow-action@0.9.1
+      with:
+        access_token: ${{ github.token }}
     - uses: actions/checkout@v2
     - name: Set up Python 3.8
       uses: actions/setup-python@v2

diff --git a/.github/workflows/pytest.yml b/.github/workflows/pytest.yml
@@ -10,6 +10,10 @@ jobs:
       matrix:
         python-version: [3.7, 3.8, 3.9]
     steps:
+    - name: Cancel previous run
+      uses: styfle/cancel-workflow-action@0.9.1
+      with:
+        access_token: ${{ github.token }}
     - uses: actions/checkout@v2
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v2

diff --git a/README.md b/README.md
@@ -281,7 +281,7 @@ Tianshou is still under development. More algorithms and features are going to b
 If you find Tianshou useful, please cite it in your publications.
 
 ```latex
-@article{weng2021tianshou,
+@article{tianshou,
   title={Tianshou: A Highly Modularized Deep Reinforcement Learning Library},
   author={Weng, Jiayi and Chen, Huayu and Yan, Dong and You, Kaichao and Duburcq, Alexis and Zhang, Minghao and Su, Hang and Zhu, Jun},
   journal={arXiv preprint arXiv:2107.14171},

diff --git a/test/base/test_collector.py b/test/base/test_collector.py
@@ -205,7 +205,7 @@ def test_collector(gym_reset_kwargs):
     # test NXEnv
     for obs_type in ["array", "object"]:
         envs = SubprocVectorEnv(
-            [lambda i=x: NXEnv(i, obs_type) for x in [5, 10, 15, 20]]
+            [lambda i=x, t=obs_type: NXEnv(i, t) for x in [5, 10, 15, 20]]
         )
         c3 = Collector(policy, envs, VectorReplayBuffer(total_size=100, buffer_num=4))
         c3.collect(n_step=6, gym_reset_kwargs=gym_reset_kwargs)
@@ -684,7 +684,7 @@ def test_collector_with_atari_setting():
 
 @pytest.mark.skipif(envpool is None, reason="EnvPool doesn't support this platform")
 def test_collector_envpool_gym_reset_return_info():
-    envs = envpool.make_gym("Pendulum-v0", num_envs=4, gym_reset_return_info=True)
+    envs = envpool.make_gym("Pendulum-v1", num_envs=4, gym_reset_return_info=True)
     policy = MyPolicy(action_shape=(len(envs), 1))
 
     c0 = Collector(

diff --git a/test/base/test_env.py b/test/base/test_env.py
@@ -214,7 +214,7 @@ def assert_get(v, expected):
 def test_env_obs_dtype():
     for obs_type in ["array", "object"]:
         envs = SubprocVectorEnv(
-            [lambda i=x: NXEnv(i, obs_type) for x in [5, 10, 15, 20]]
+            [lambda i=x, t=obs_type: NXEnv(i, t) for x in [5, 10, 15, 20]]
         )
         obs = envs.reset()
         assert obs.dtype == object

diff --git a/test/continuous/test_sac_with_il.py b/test/continuous/test_sac_with_il.py
@@ -21,7 +21,7 @@
 
 def get_args():
     parser = argparse.ArgumentParser()
-    parser.add_argument('--task', type=str, default='Pendulum-v0')
+    parser.add_argument('--task', type=str, default='Pendulum-v1')
     parser.add_argument('--reward-threshold', type=float, default=None)
     parser.add_argument('--seed', type=int, default=1)
     parser.add_argument('--buffer-size', type=int, default=20000)

diff --git a/tianshou/__init__.py b/tianshou/__init__.py
@@ -1,6 +1,6 @@
 from tianshou import data, env, exploration, policy, trainer, utils
 
-__version__ = "0.4.8"
+__version__ = "0.4.9"
 
 __all__ = [
     "env",