Merge branch 'main' into rewrite_iql_example

pytorch · Nov 30, 2023 · 76eb7d5 · 76eb7d5
2 parents 6d0c1f0 + 6c27bdb
commit 76eb7d5
Show file tree

Hide file tree

Showing 69 changed files with 3,008 additions and 1,018 deletions.
diff --git a/.github/pytorch-probot.yml b/.github/pytorch-probot.yml
@@ -0,0 +1,5 @@
+# List of workflows that will be re-run in case of failures
+# https://github.com/pytorch/test-infra/blob/main/torchci/lib/bot/retryBot.ts
+retryable_workflows:
+- Build M1
+- Wheels
diff --git a/.github/unittest/linux_examples/scripts/run_test.sh b/.github/unittest/linux_examples/scripts/run_test.sh
@@ -58,6 +58,12 @@ python .github/unittest/helpers/coverage_run_parallel.py examples/cql/cql_offlin
 # ==================================================================================== #
 # ================================ Gymnasium ========================================= #
 
+python .github/unittest/helpers/coverage_run_parallel.py examples/impala/impala_single_node.py \
+  collector.total_frames=80 \
+  collector.frames_per_batch=20 \
+  collector.num_workers=1 \
+  logger.backend= \
+  logger.test_interval=10
 python .github/unittest/helpers/coverage_run_parallel.py examples/ppo/ppo_mujoco.py \
   env.env_name=HalfCheetah-v4 \
   collector.total_frames=40 \

diff --git a/.github/workflows/benchmarks.yml b/.github/workflows/benchmarks.yml
@@ -34,7 +34,8 @@ jobs:
           python -m pip install git+https://github.com/pytorch/tensordict 
           python setup.py develop
           python -m pip install pytest pytest-benchmark
-          python -m pip install dm_control
+          python3 -m pip install "gym[accept-rom-license,atari]"
+          python3 -m pip install dm_control
       - name: Run benchmarks
         run: |
           cd benchmarks/
@@ -57,62 +58,65 @@ jobs:
 
   benchmark_gpu:
     name: GPU Pytest benchmark
-    runs-on: ubuntu-20.04
-    strategy:
-      matrix:
-        include:
-         - os: linux.4xlarge.nvidia.gpu
-           python-version: 3.8
+    runs-on: linux.g5.4xlarge.nvidia.gpu
     defaults:
       run:
         shell: bash -l {0}
-    container: nvidia/cuda:11.8.0-cudnn8-devel-ubuntu20.04
+    container:
+      image: nvidia/cuda:12.3.0-base-ubuntu22.04
+      options: --gpus all
     steps:
-    - name: Install deps
-      run: |
-        export TZ=Europe/London
-        export DEBIAN_FRONTEND=noninteractive  # tzdata bug
-        apt-get update -y
-        apt-get install software-properties-common -y
-        add-apt-repository ppa:git-core/candidate -y
-        apt-get update -y
-        apt-get upgrade -y
-        apt-get -y install libglu1-mesa libgl1-mesa-glx libosmesa6 gcc curl g++ unzip wget libglfw3-dev libgles2-mesa-dev libglew-dev sudo git cmake libz-dev
-    - name: Check ldd --version
-      run: ldd --version
-    - name: Checkout
-      uses: actions/checkout@v3
-    - name: Update pip
-      run: |
-        apt-get install python3.8 python3-pip -y
-        pip3 install --upgrade pip
-    - name: Setup git
-      run: git config --global --add safe.directory /__w/rl/rl
-    - name: setup Path
-      run: |
-        echo /usr/local/bin >> $GITHUB_PATH
-    - name: Setup Environment
-      run: |
-        python3 -m pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu118 
-        python3 -m pip install git+https://github.com/pytorch/tensordict 
-        python3 setup.py develop
-        python3 -m pip install pytest pytest-benchmark
-        python3 -m pip install dm_control
-    - name: Run benchmarks
-      run: |
-        cd benchmarks/
-        python3 -m pytest --benchmark-json output.json
-    - name: Store benchmark results
-      uses: benchmark-action/github-action-benchmark@v1
-      if: ${{ github.ref == 'refs/heads/main' || github.event_name == 'workflow_dispatch' }}
-      with:
-        name: GPU Benchmark Results
-        tool: 'pytest'
-        output-file-path: benchmarks/output.json
-        fail-on-alert: true
-        alert-threshold: '200%'
-        alert-comment-cc-users: '@vmoens'
-        comment-on-alert: true
-        github-token: ${{ secrets.GITHUB_TOKEN }}
-        gh-pages-branch: gh-pages
-        auto-push: true
+      - name: Install deps
+        run: |
+          export TZ=Europe/London
+          export DEBIAN_FRONTEND=noninteractive  # tzdata bug
+          apt-get update -y
+          apt-get install software-properties-common -y
+          add-apt-repository ppa:git-core/candidate -y
+          apt-get update -y
+          apt-get upgrade -y
+          apt-get -y install libglu1-mesa libgl1-mesa-glx libosmesa6 gcc curl g++ unzip wget libglfw3-dev libgles2-mesa-dev libglew-dev sudo git cmake libz-dev
+      - name: Check ldd --version
+        run: ldd --version
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Python Setup
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.8
+      - name: Setup git
+        run: git config --global --add safe.directory /__w/rl/rl
+      - name: setup Path
+        run: |
+          echo /usr/local/bin >> $GITHUB_PATH
+      - name: Setup Environment
+        run: |
+          python3 -m pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu121
+          python3 -m pip install git+https://github.com/pytorch/tensordict 
+          python3 setup.py develop
+          python3 -m pip install pytest pytest-benchmark
+          python3 -m pip install "gym[accept-rom-license,atari]"
+          python3 -m pip install dm_control
+      - name: check GPU presence
+        run: |
+          python -c """import torch
+          assert torch.cuda.device_count()
+          """
+      - name: Run benchmarks
+        run: |
+          cd benchmarks/
+          python3 -m pytest --benchmark-json output.json
+      - name: Store benchmark results
+        uses: benchmark-action/github-action-benchmark@v1
+        if: ${{ github.ref == 'refs/heads/main' || github.event_name == 'workflow_dispatch' }}
+        with:
+          name: GPU Benchmark Results
+          tool: 'pytest'
+          output-file-path: benchmarks/output.json
+          fail-on-alert: true
+          alert-threshold: '200%'
+          alert-comment-cc-users: '@vmoens'
+          comment-on-alert: true
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          gh-pages-branch: gh-pages
+          auto-push: true
diff --git a/.github/workflows/benchmarks_pr.yml b/.github/workflows/benchmarks_pr.yml
@@ -33,7 +33,8 @@ jobs:
           python -m pip install git+https://github.com/pytorch/tensordict 
           python setup.py develop
           python -m pip install pytest pytest-benchmark
-          python -m pip install dm_control
+          python3 -m pip install "gym[accept-rom-license,atari]"
+          python3 -m pip install dm_control
       - name: Setup benchmarks
         run: |
           echo "BASE_SHA=$(echo ${{ github.event.pull_request.base.sha }} | cut -c1-8)" >> $GITHUB_ENV
@@ -63,75 +64,78 @@ jobs:
 
   benchmark_gpu:
     name: GPU Pytest benchmark
-    runs-on: ubuntu-20.04
-    strategy:
-      matrix:
-        include:
-         - os: linux.4xlarge.nvidia.gpu
-           python-version: 3.8
+    runs-on: linux.g5.4xlarge.nvidia.gpu
     defaults:
       run:
         shell: bash -l {0}
-    container: nvidia/cuda:11.8.0-cudnn8-devel-ubuntu20.04
+    container:
+      image: nvidia/cuda:12.3.0-base-ubuntu22.04
+      options: --gpus all
     steps:
-    - name: Who triggered this?
-      run: |
-        echo "Action triggered by ${{ github.event.pull_request.html_url }}"
-    - name: Install deps
-      run: |
-        export TZ=Europe/London
-        export DEBIAN_FRONTEND=noninteractive  # tzdata bug
-        apt-get update -y
-        apt-get install software-properties-common -y
-        add-apt-repository ppa:git-core/candidate -y
-        apt-get update -y
-        apt-get upgrade -y
-        apt-get -y install libglu1-mesa libgl1-mesa-glx libosmesa6 gcc curl g++ unzip wget libglfw3-dev libgles2-mesa-dev libglew-dev sudo git cmake libz-dev
-    - name: Check ldd --version
-      run: ldd --version
-    - name: Checkout
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 50 # this is to make sure we obtain the target base commit
-    - name: Update pip
-      run: |
-        apt-get install python3.8 python3-pip -y
-        pip3 install --upgrade pip
-    - name: Setup git
-      run: git config --global --add safe.directory /__w/rl/rl
-    - name: setup Path
-      run: |
-        echo /usr/local/bin >> $GITHUB_PATH
-    - name: Setup Environment
-      run: |
-        python3 -m pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu118 
-        python3 -m pip install git+https://github.com/pytorch/tensordict 
-        python3 setup.py develop
-        python3 -m pip install pytest pytest-benchmark
-        python3 -m pip install dm_control
-    - name: Setup benchmarks
-      run: |
-        echo "BASE_SHA=$(echo ${{ github.event.pull_request.base.sha }} | cut -c1-8)" >> $GITHUB_ENV
-        echo "HEAD_SHA=$(echo ${{ github.event.pull_request.head.sha }} | cut -c1-8)" >> $GITHUB_ENV
-        echo "BASELINE_JSON=$(mktemp)" >> $GITHUB_ENV
-        echo "CONTENDER_JSON=$(mktemp)" >> $GITHUB_ENV
-        echo "PR_COMMENT=$(mktemp)" >>  $GITHUB_ENV
-    - name: Run benchmarks
-      run: |
-        cd benchmarks/
-        RUN_BENCHMARK="pytest --rank 0 --benchmark-json "
-        git checkout ${{ github.event.pull_request.base.sha }}
-        $RUN_BENCHMARK ${{ env.BASELINE_JSON }}
-        git checkout ${{ github.event.pull_request.head.sha }}
-        $RUN_BENCHMARK ${{ env.CONTENDER_JSON }}
-    - name: Publish results
-      uses: apbard/pytest-benchmark-commenter@v3
-      with:
-        token: ${{ secrets.GITHUB_TOKEN }}
-        benchmark-file: ${{ env.CONTENDER_JSON }}
-        comparison-benchmark-file: ${{ env.BASELINE_JSON }}
-        benchmark-metrics: 'name,max,mean,ops'
-        comparison-benchmark-metric: 'ops'
-        comparison-higher-is-better: true
-        comparison-threshold: 5
-        benchmark-title: 'Result of GPU Benchmark Tests'
+      - name: Who triggered this?
+        run: |
+          echo "Action triggered by ${{ github.event.pull_request.html_url }}"
+      - name: Install deps
+        run: |
+          export TZ=Europe/London
+          export DEBIAN_FRONTEND=noninteractive  # tzdata bug
+          apt-get update -y
+          apt-get install software-properties-common -y
+          add-apt-repository ppa:git-core/candidate -y
+          apt-get update -y
+          apt-get upgrade -y
+          apt-get -y install libglu1-mesa libgl1-mesa-glx libosmesa6 gcc curl g++ unzip wget libglfw3-dev libgles2-mesa-dev libglew-dev sudo git cmake libz-dev
+      - name: Check ldd --version
+        run: ldd --version
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 50 # this is to make sure we obtain the target base commit
+      - name: Python Setup
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.8
+      - name: Setup git
+        run: git config --global --add safe.directory /__w/rl/rl
+      - name: setup Path
+        run: |
+          echo /usr/local/bin >> $GITHUB_PATH
+      - name: Setup Environment
+        run: |
+          python3 -m pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu121
+          python3 -m pip install git+https://github.com/pytorch/tensordict 
+          python3 setup.py develop
+          python3 -m pip install pytest pytest-benchmark
+          python3 -m pip install "gym[accept-rom-license,atari]"
+          python3 -m pip install dm_control
+      - name: check GPU presence
+        run: |
+          python -c """import torch
+          assert torch.cuda.device_count()
+          """
+      - name: Setup benchmarks
+        run: |
+          echo "BASE_SHA=$(echo ${{ github.event.pull_request.base.sha }} | cut -c1-8)" >> $GITHUB_ENV
+          echo "HEAD_SHA=$(echo ${{ github.event.pull_request.head.sha }} | cut -c1-8)" >> $GITHUB_ENV
+          echo "BASELINE_JSON=$(mktemp)" >> $GITHUB_ENV
+          echo "CONTENDER_JSON=$(mktemp)" >> $GITHUB_ENV
+          echo "PR_COMMENT=$(mktemp)" >>  $GITHUB_ENV
+      - name: Run benchmarks
+        run: |
+          cd benchmarks/
+          RUN_BENCHMARK="pytest --rank 0 --benchmark-json "
+          git checkout ${{ github.event.pull_request.base.sha }}
+          $RUN_BENCHMARK ${{ env.BASELINE_JSON }}
+          git checkout ${{ github.event.pull_request.head.sha }}
+          $RUN_BENCHMARK ${{ env.CONTENDER_JSON }}
+      - name: Publish results
+        uses: apbard/pytest-benchmark-commenter@v3
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          benchmark-file: ${{ env.CONTENDER_JSON }}
+          comparison-benchmark-file: ${{ env.BASELINE_JSON }}
+          benchmark-metrics: 'name,max,mean,ops'
+          comparison-benchmark-metric: 'ops'
+          comparison-higher-is-better: true
+          comparison-threshold: 5
+          benchmark-title: 'Result of GPU Benchmark Tests'
diff --git a/README.md b/README.md
@@ -9,7 +9,7 @@
 <a href="https://pypi.org/project/torchrl-nightly"><img src="https://img.shields.io/pypi/v/torchrl-nightly?label=nightly" alt="pypi nightly version"></a>
 [![Downloads](https://static.pepy.tech/personalized-badge/torchrl?period=total&units=international_system&left_color=blue&right_color=orange&left_text=Downloads)](https://pepy.tech/project/torchrl)
 [![Downloads](https://static.pepy.tech/personalized-badge/torchrl-nightly?period=total&units=international_system&left_color=blue&right_color=orange&left_text=Downloads%20(nightly))](https://pepy.tech/project/torchrl-nightly)
-[![Discord Shield](https://dcbadge.vercel.app/api/server/xSURYdvu)](https://discord.gg/xSURYdvu)
+[![Discord Shield](https://dcbadge.vercel.app/api/server/cZs26Qq3Dd)](https://discord.gg/cZs26Qq3Dd)
 
 # TorchRL