From 902502f6db45addeaa670c06cb8f06caaab3b272 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 10 Jun 2024 10:56:52 +0200
Subject: [PATCH 1/8] fix ci macos

---
 .github/workflows/build.yml | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index f4177f5e..fdb71c91 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -7,8 +7,12 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
+        os: [ubuntu-latest, macos-latest, macos-13, windows-latest]
         python-version: ['3.7', '3.8', '3.9', '3.10']
+        exclude:
+          # Exclude the combination of macOS-latest and Python 3.7 as arm64 doesn't support Python 3.7
+          - os: macos-latest
+            python-version: '3.7'
     steps:
     - uses: actions/checkout@v3
     - name: Set up Python ${{ matrix.python-version }}

From 0d17e18cb4e51207e95de4aae70c17dcc51ed84d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 10 Jun 2024 11:02:38 +0200
Subject: [PATCH 2/8] is_success consistency

---
 panda_gym/envs/tasks/flip.py           | 2 +-
 panda_gym/envs/tasks/pick_and_place.py | 2 +-
 panda_gym/envs/tasks/push.py           | 2 +-
 panda_gym/envs/tasks/reach.py          | 2 +-
 panda_gym/envs/tasks/slide.py          | 2 +-
 panda_gym/envs/tasks/stack.py          | 2 +-
 6 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/panda_gym/envs/tasks/flip.py b/panda_gym/envs/tasks/flip.py
index 1df64ceb..70723815 100644
--- a/panda_gym/envs/tasks/flip.py
+++ b/panda_gym/envs/tasks/flip.py
@@ -78,7 +78,7 @@ def _sample_object(self) -> Tuple[np.ndarray, np.ndarray]:
         object_rotation = np.zeros(3)
         return object_position, object_rotation
 
-    def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray) -> np.ndarray:
+    def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = angle_distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
diff --git a/panda_gym/envs/tasks/pick_and_place.py b/panda_gym/envs/tasks/pick_and_place.py
index 47ef2c31..4ac55f1c 100644
--- a/panda_gym/envs/tasks/pick_and_place.py
+++ b/panda_gym/envs/tasks/pick_and_place.py
@@ -83,7 +83,7 @@ def _sample_object(self) -> np.ndarray:
         object_position += noise
         return object_position
 
-    def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray) -> np.ndarray:
+    def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
diff --git a/panda_gym/envs/tasks/push.py b/panda_gym/envs/tasks/push.py
index 364fd9d2..e3b53af5 100644
--- a/panda_gym/envs/tasks/push.py
+++ b/panda_gym/envs/tasks/push.py
@@ -85,7 +85,7 @@ def _sample_object(self) -> np.ndarray:
         object_position += noise
         return object_position
 
-    def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray) -> np.ndarray:
+    def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
diff --git a/panda_gym/envs/tasks/reach.py b/panda_gym/envs/tasks/reach.py
index 9949dcf2..abca7d47 100644
--- a/panda_gym/envs/tasks/reach.py
+++ b/panda_gym/envs/tasks/reach.py
@@ -52,7 +52,7 @@ def _sample_goal(self) -> np.ndarray:
         goal = self.np_random.uniform(self.goal_range_low, self.goal_range_high)
         return goal
 
-    def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray) -> np.ndarray:
+    def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
diff --git a/panda_gym/envs/tasks/slide.py b/panda_gym/envs/tasks/slide.py
index 04911360..047fb215 100644
--- a/panda_gym/envs/tasks/slide.py
+++ b/panda_gym/envs/tasks/slide.py
@@ -89,7 +89,7 @@ def _sample_object(self) -> np.ndarray:
         object_position += noise
         return object_position
 
-    def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray) -> np.ndarray:
+    def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
diff --git a/panda_gym/envs/tasks/stack.py b/panda_gym/envs/tasks/stack.py
index cde63cc1..919adabc 100644
--- a/panda_gym/envs/tasks/stack.py
+++ b/panda_gym/envs/tasks/stack.py
@@ -117,7 +117,7 @@ def _sample_objects(self) -> Tuple[np.ndarray, np.ndarray]:
         # if distance(object1_position, object2_position) > 0.1:
         return object1_position, object2_position
 
-    def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray) -> np.ndarray:
+    def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         # must be vectorized !!
         d = distance(achieved_goal, desired_goal)
         return np.array((d < self.distance_threshold), dtype=bool)

From ea82d34c9da41a6de70f79223c989eedfff3d775 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 10 Jun 2024 11:12:05 +0200
Subject: [PATCH 3/8] signature for compute_reward

---
 panda_gym/envs/tasks/flip.py           | 2 +-
 panda_gym/envs/tasks/pick_and_place.py | 2 +-
 panda_gym/envs/tasks/push.py           | 2 +-
 panda_gym/envs/tasks/reach.py          | 2 +-
 panda_gym/envs/tasks/slide.py          | 2 +-
 panda_gym/envs/tasks/stack.py          | 2 +-
 6 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/panda_gym/envs/tasks/flip.py b/panda_gym/envs/tasks/flip.py
index 70723815..6a549332 100644
--- a/panda_gym/envs/tasks/flip.py
+++ b/panda_gym/envs/tasks/flip.py
@@ -82,7 +82,7 @@ def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info:
         d = angle_distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
-    def compute_reward(self, achieved_goal, desired_goal, info: Dict[str, Any]) -> np.ndarray:
+    def compute_reward(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = angle_distance(achieved_goal, desired_goal)
         if self.reward_type == "sparse":
             return -np.array(d > self.distance_threshold, dtype=np.float32)
diff --git a/panda_gym/envs/tasks/pick_and_place.py b/panda_gym/envs/tasks/pick_and_place.py
index 4ac55f1c..610505c3 100644
--- a/panda_gym/envs/tasks/pick_and_place.py
+++ b/panda_gym/envs/tasks/pick_and_place.py
@@ -87,7 +87,7 @@ def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info:
         d = distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
-    def compute_reward(self, achieved_goal, desired_goal, info: Dict[str, Any]) -> np.ndarray:
+    def compute_reward(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         if self.reward_type == "sparse":
             return -np.array(d > self.distance_threshold, dtype=np.float32)
diff --git a/panda_gym/envs/tasks/push.py b/panda_gym/envs/tasks/push.py
index e3b53af5..d32322a4 100644
--- a/panda_gym/envs/tasks/push.py
+++ b/panda_gym/envs/tasks/push.py
@@ -89,7 +89,7 @@ def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info:
         d = distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
-    def compute_reward(self, achieved_goal, desired_goal, info: Dict[str, Any]) -> np.ndarray:
+    def compute_reward(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         if self.reward_type == "sparse":
             return -np.array(d > self.distance_threshold, dtype=np.float32)
diff --git a/panda_gym/envs/tasks/reach.py b/panda_gym/envs/tasks/reach.py
index abca7d47..3a3cdd15 100644
--- a/panda_gym/envs/tasks/reach.py
+++ b/panda_gym/envs/tasks/reach.py
@@ -56,7 +56,7 @@ def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info:
         d = distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
-    def compute_reward(self, achieved_goal, desired_goal, info: Dict[str, Any]) -> np.ndarray:
+    def compute_reward(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         if self.reward_type == "sparse":
             return -np.array(d > self.distance_threshold, dtype=np.float32)
diff --git a/panda_gym/envs/tasks/slide.py b/panda_gym/envs/tasks/slide.py
index 047fb215..3c40f5bb 100644
--- a/panda_gym/envs/tasks/slide.py
+++ b/panda_gym/envs/tasks/slide.py
@@ -93,7 +93,7 @@ def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info:
         d = distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
-    def compute_reward(self, achieved_goal, desired_goal, info: Dict[str, Any]) -> np.ndarray:
+    def compute_reward(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         if self.reward_type == "sparse":
             return -np.array(d > self.distance_threshold, dtype=np.float32)
diff --git a/panda_gym/envs/tasks/stack.py b/panda_gym/envs/tasks/stack.py
index 919adabc..85510766 100644
--- a/panda_gym/envs/tasks/stack.py
+++ b/panda_gym/envs/tasks/stack.py
@@ -122,7 +122,7 @@ def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info:
         d = distance(achieved_goal, desired_goal)
         return np.array((d < self.distance_threshold), dtype=bool)
 
-    def compute_reward(self, achieved_goal, desired_goal, info: Dict[str, Any]) -> np.ndarray:
+    def compute_reward(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         if self.reward_type == "sparse":
             return -np.array((d > self.distance_threshold), dtype=np.float32)

From 3a6cf6a81aa99fcb18eef43adb413278447682ac Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 10 Jun 2024 11:41:01 +0200
Subject: [PATCH 4/8] update actions versions

---
 .github/workflows/build.yml | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index fdb71c91..2b1023e2 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -14,9 +14,9 @@ jobs:
           - os: macos-latest
             python-version: '3.7'
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
@@ -38,13 +38,13 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - name: Checkout code
-      uses: actions/checkout@v2
+      uses: actions/checkout@v4
     - name: Download coverage reports
-      uses: actions/download-artifact@v2
+      uses: actions/download-artifact@v4
       with:
         name: coverage-report
     - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v3
+      uses: codecov/codecov-action@v4
       with:
         directory: ./coverage/reports/
         fail_ci_if_error: true
@@ -54,9 +54,9 @@ jobs:
   codestyle_type_and_doc:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set up Python 3.8
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: 3.8
     - name: Install dependencies

From 1e8773686c1f1cd3a628221b0184bc2c1945967e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 10 Jun 2024 11:45:38 +0200
Subject: [PATCH 5/8] try another ci

---
 .github/workflows/build.yml | 62 ++++++++++++++++++++-----------------
 1 file changed, 33 insertions(+), 29 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 2b1023e2..2e10a637 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -14,62 +14,66 @@ jobs:
           - os: macos-latest
             python-version: '3.7'
     steps:
+    # Check out the repository code
     - uses: actions/checkout@v4
+    
+    # Set up the specified Python version
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
+    
+    # Install dependencies
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
         pip install -e .
         pip install pytest-cov
+    
+    # Run tests with pytest and generate coverage report
     - name: Test with pytest
       run: |
         pytest --cov=./ --cov-report=xml
+    
+    # Upload the coverage report as an artifact
     - name: Save coverage report
       uses: actions/upload-artifact@v2
       with:
         name: coverage-report
         path: ./coverage.xml
-
-  upload-coverage:
-    needs: test
-    runs-on: ubuntu-latest
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
-    - name: Download coverage reports
-      uses: actions/download-artifact@v4
-      with:
-        name: coverage-report
-    - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v4
-      with:
-        directory: ./coverage/reports/
-        fail_ci_if_error: true
-        files: ./coverage.xml
-        name: codecov-umbrella
-        verbose: true
-  codestyle_type_and_doc:
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python 3.8
-      uses: actions/setup-python@v5
-      with:
-        python-version: 3.8
-    - name: Install dependencies
+    
+    # Additional steps only for ubuntu-latest and Python 3.10
+    # Install development dependencies
+    - name: Install dev dependencies
+      if: matrix.os == 'ubuntu-latest' && matrix.python-version == '3.10'
       run: |
-        python -m pip install --upgrade pip
         pip install -e .[develop]
+    
+    # Run Pytype for type checking
     - name: Pytype
+      if: matrix.os == 'ubuntu-latest' && matrix.python-version == '3.10'
       run: |
         pytype panda_gym
+    
+    # Check code style with black and isort
     - name: Check codestyle
+      if: matrix.os == 'ubuntu-latest' && matrix.python-version == '3.10'
       run: |
         black -l 127 --check panda_gym test
         isort -l 127 --profile black --check panda_gym test
+    
+    # Build documentation
     - name: Make docs
+      if: matrix.os == 'ubuntu-latest' && matrix.python-version == '3.10'
       run: |
         make html
+    
+    # Upload coverage to Codecov
+    - name: Upload coverage to Codecov
+      if: matrix.os == 'ubuntu-latest' && matrix.python-version == '3.10'
+      uses: codecov/codecov-action@v4
+      with:
+        files: ./coverage.xml
+        fail_ci_if_error: true
+        name: codecov-umbrella
+        verbose: true

From cd505a14f66fb32c9d4b0dbee8a6bbc514b6af78 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 10 Jun 2024 11:48:34 +0200
Subject: [PATCH 6/8] secret token

---
 .github/workflows/build.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 2e10a637..0698e6b4 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -77,3 +77,4 @@ jobs:
         fail_ci_if_error: true
         name: codecov-umbrella
         verbose: true
+        token: ${{ secrets.CODECOV_TOKEN }} # required

From f87b40bc603df0f5582093a6b8bea5b3caac9d17 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 10 Jun 2024 11:52:47 +0200
Subject: [PATCH 7/8] build only pr

---
 .github/workflows/build.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 0698e6b4..70e849e8 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -1,6 +1,6 @@
 name: build
 
-on: [push, pull_request]
+on: [pull_request]
 
 jobs:
   test:
@@ -37,7 +37,7 @@ jobs:
     
     # Upload the coverage report as an artifact
     - name: Save coverage report
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: coverage-report
         path: ./coverage.xml

From a29561e53355d96060e011b36101f3d1e8eee598 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 10 Jun 2024 11:56:44 +0200
Subject: [PATCH 8/8] upload only py3.10

---
 .github/workflows/build.yml | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 70e849e8..0b45741c 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -35,14 +35,15 @@ jobs:
       run: |
         pytest --cov=./ --cov-report=xml
     
+    # Additional steps only for ubuntu-latest and Python 3.10
     # Upload the coverage report as an artifact
     - name: Save coverage report
+      if: matrix.os == 'ubuntu-latest' && matrix.python-version == '3.10'
       uses: actions/upload-artifact@v4
       with:
         name: coverage-report
         path: ./coverage.xml
-    
-    # Additional steps only for ubuntu-latest and Python 3.10
+
     # Install development dependencies
     - name: Install dev dependencies
       if: matrix.os == 'ubuntu-latest' && matrix.python-version == '3.10'