cusrl 1.0.0__tar.gz

cusrl-1.0.0/.github/workflows/python-app.yml

@@ -0,0 +1,47 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: Python application
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [ "3.10", "3.11", "3.12", "3.13" ]
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v3
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Display Python version
+        run: python -c "import sys; print(sys.version)"
+      - name: Install dependencies
+        run: |
+          rm ~/.cache/pip -rf
+          python -m pip install --upgrade pip
+          pip install flake8 pytest
+          pip install --no-cache-dir .[all]
+      - name: Lint with flake8
+        run: |
+          # stop the build if there are Python syntax errors or undefined names
+          flake8 . --count --select=E9,F63,F7,F82 --extend-ignore=E203 --show-source --statistics
+          # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+          flake8 . --count --exit-zero --extend-ignore=E203 --max-complexity=10 --max-line-length=127 --statistics
+      - name: Display device and autocast availability
+        run: |
+           python -c "import cusrl; print(cusrl.device(), cusrl.utils.is_autocast_available())"
+      - name: Test with pytest
+        run: |
+          pytest

cusrl-1.0.0/.gitignore

@@ -0,0 +1,183 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# IDE
+.idea/
+.vscode/
+.zed/
+
+# Logs
+logs/
+wandb/

cusrl-1.0.0/.pre-commit-config.yaml

@@ -0,0 +1,28 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+  - repo: https://github.com/psf/black
+    rev: 25.1.0
+    hooks:
+      - id: black
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.4.1
+    hooks:
+      - id: codespell
+        additional_dependencies: [ tomli ]
+  - repo: https://github.com/pycqa/isort
+    rev: 6.0.1
+    hooks:
+      - id: isort
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.20.0
+    hooks:
+      - id: pyupgrade
+        args: [ "--py310-plus" ]

cusrl-1.0.0/PKG-INFO

@@ -0,0 +1,109 @@
+Metadata-Version: 2.4
+Name: cusrl
+Version: 1.0.0
+Summary: Customizable and modular RL algorithms implemented in PyTorch
+Author-email: Chengrui Zhu <jewel@zju.edu.cn>
+Keywords: reinforcement-learning,pytorch,rl
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: numpy>=1.26.0
+Requires-Dist: torch>=2.4.0
+Requires-Dist: objprint~=0.3.0
+Requires-Dist: gymnasium>=1.1.0
+Requires-Dist: pyyaml~=6.0.2
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Provides-Extra: onnx
+Requires-Dist: onnx; extra == "onnx"
+Requires-Dist: onnxruntime; extra == "onnx"
+Requires-Dist: onnxscript; extra == "onnx"
+Provides-Extra: tensorboard
+Requires-Dist: tensorboard; extra == "tensorboard"
+Provides-Extra: wandb
+Requires-Dist: wandb; extra == "wandb"
+Provides-Extra: all
+Requires-Dist: pytest; extra == "all"
+Requires-Dist: onnx; extra == "all"
+Requires-Dist: onnxruntime; extra == "all"
+Requires-Dist: onnxscript; extra == "all"
+Requires-Dist: tensorboard; extra == "all"
+Requires-Dist: wandb; extra == "all"
+
+# CusRL: Customizable Reinforcement Learning
+
+CusRL is a flexible and modular reinforcement learning framework that emphasizes customization.
+Its clean and decoupled implementation allows researchers to easily integrate new components,
+which is particularly useful for advancements in robotics learning.
+
+> **Note:** This project is under **active development**, which means the interface is unstable
+and breaking changes are likely to occur frequently.
+
+## Installation
+
+Requires Python >= 3.10.
+
+```bash
+git clone https://github.com/chengruiz/cusrl.git
+# Minimal installation
+pip install -e . --config-settings editable_mode=strict
+# Install with all optional dependencies
+pip install -e .[all] --config-settings editable_mode=strict
+# For development, install pre-commit (assuming you have pre-commit installed)
+pre-commit install
+```
+
+## Quick Start
+
+Try to train a PPO agent with CusRL and evaluate it:
+
+```bash
+python -m cusrl.launch.train -env MountainCar-v0 -alg ppo --logger tensorboard --seed 42
+python -m cusrl.launch.play --checkpoint logs/MountainCar-v0:ppo
+```
+
+Or if you have [IssacLab](https://github.com/isaac-sim/IsaacLab) installed:
+
+```bash
+python -m cusrl.launch.train -env Isaac-Velocity-Rough-Anymal-C-v0 -alg ppo \
+    --logger tensorboard --environment-args="--headless"
+python -m cusrl.launch.play --checkpoint logs/Isaac-Velocity-Rough-Anymal-C-v0:ppo
+```
+
+Try distributed training:
+
+```bash
+torchrun --nproc-per-node=2 -m cusrl.launch.train -env Isaac-Velocity-Rough-Anymal-C-v0 \
+    -alg ppo --logger tensorboard --environment-args="--headless"
+```
+
+## Highlights
+
+CusRL provides a modular and extensible framework for RL with the following key features:
+
+- **Modular Design**: Components are highly decoupled, allowing for easy customization and extension
+- **Diverse Network Architectures**: Support for MLP, CNN, RNNs, Transformer and custom architectures
+- **Modern Training Techniques**: Built-in support for distributed and mixed-precision training
+
+CusRL is designed for researchers and practitioners who need a clean, extensible framework for implementing
+and experimenting with reinforcement learning algorithms. The architecture emphasizes clean separation of
+concerns, allowing users to modify specific components without disrupting the rest of the system.
+
+## Implemented Algorithms
+
+- [Proximal Policy Optimization (PPO)](https://arxiv.org/abs/1707.06347) with recurrent policy support
+- [Generalized Advantage Estimation (GAE)](https://arxiv.org/abs/1506.02438)
+  with [distinct lambda values](https://proceedings.neurips.cc/paper_files/paper/2022/hash/e95475f5fb8edb9075bf9e25670d4013-Abstract-Conference.html)
+- [Preserving Outputs Precisely, while Adaptively Rescaling Targets (Pop-Art)](https://proceedings.neurips.cc/paper/2016/hash/5227b6aaf294f5f027273aebf16015f2-Abstract.html)
+- [Random Network Distillation (RND)](https://arxiv.org/abs/1810.12894)
+- Symmetry Augmentations:
+  [Symmetry Loss](https://dl.acm.org/doi/abs/10.1145/3197517.3201397),
+  [Symmetric Architecture](https://dl.acm.org/doi/abs/10.1145/3359566.3360070),
+  [Symmetric Data Augmentation](https://ieeexplore.ieee.org/abstract/document/10611493)
+
+## Cite
+
+If you find this framework useful for your research, please consider citing our work on legged locomotion:
+
+- [Efficient Learning of A Unified Policy For Whole-body Manipulation and Locomotion Skills](https://www.arxiv.org/abs/2507.04229), Accepted by IROS 2025
+- [Learning Accurate and Robust Velocity Tracking for Quadrupedal Robots](https://www.authorea.com/doi/full/10.22541/au.173321917.73583610), Accepted by JFR
+- [Learning Safe Locomotion for Quadrupedal Robots by Derived-Action Optimization](https://ieeexplore.ieee.org/abstract/document/10802725), Published in IROS 2024

cusrl-1.0.0/README.md

@@ -0,0 +1,78 @@
+# CusRL: Customizable Reinforcement Learning
+
+CusRL is a flexible and modular reinforcement learning framework that emphasizes customization.
+Its clean and decoupled implementation allows researchers to easily integrate new components,
+which is particularly useful for advancements in robotics learning.
+
+> **Note:** This project is under **active development**, which means the interface is unstable
+and breaking changes are likely to occur frequently.
+
+## Installation
+
+Requires Python >= 3.10.
+
+```bash
+git clone https://github.com/chengruiz/cusrl.git
+# Minimal installation
+pip install -e . --config-settings editable_mode=strict
+# Install with all optional dependencies
+pip install -e .[all] --config-settings editable_mode=strict
+# For development, install pre-commit (assuming you have pre-commit installed)
+pre-commit install
+```
+
+## Quick Start
+
+Try to train a PPO agent with CusRL and evaluate it:
+
+```bash
+python -m cusrl.launch.train -env MountainCar-v0 -alg ppo --logger tensorboard --seed 42
+python -m cusrl.launch.play --checkpoint logs/MountainCar-v0:ppo
+```
+
+Or if you have [IssacLab](https://github.com/isaac-sim/IsaacLab) installed:
+
+```bash
+python -m cusrl.launch.train -env Isaac-Velocity-Rough-Anymal-C-v0 -alg ppo \
+    --logger tensorboard --environment-args="--headless"
+python -m cusrl.launch.play --checkpoint logs/Isaac-Velocity-Rough-Anymal-C-v0:ppo
+```
+
+Try distributed training:
+
+```bash
+torchrun --nproc-per-node=2 -m cusrl.launch.train -env Isaac-Velocity-Rough-Anymal-C-v0 \
+    -alg ppo --logger tensorboard --environment-args="--headless"
+```
+
+## Highlights
+
+CusRL provides a modular and extensible framework for RL with the following key features:
+
+- **Modular Design**: Components are highly decoupled, allowing for easy customization and extension
+- **Diverse Network Architectures**: Support for MLP, CNN, RNNs, Transformer and custom architectures
+- **Modern Training Techniques**: Built-in support for distributed and mixed-precision training
+
+CusRL is designed for researchers and practitioners who need a clean, extensible framework for implementing
+and experimenting with reinforcement learning algorithms. The architecture emphasizes clean separation of
+concerns, allowing users to modify specific components without disrupting the rest of the system.
+
+## Implemented Algorithms
+
+- [Proximal Policy Optimization (PPO)](https://arxiv.org/abs/1707.06347) with recurrent policy support
+- [Generalized Advantage Estimation (GAE)](https://arxiv.org/abs/1506.02438)
+  with [distinct lambda values](https://proceedings.neurips.cc/paper_files/paper/2022/hash/e95475f5fb8edb9075bf9e25670d4013-Abstract-Conference.html)
+- [Preserving Outputs Precisely, while Adaptively Rescaling Targets (Pop-Art)](https://proceedings.neurips.cc/paper/2016/hash/5227b6aaf294f5f027273aebf16015f2-Abstract.html)
+- [Random Network Distillation (RND)](https://arxiv.org/abs/1810.12894)
+- Symmetry Augmentations:
+  [Symmetry Loss](https://dl.acm.org/doi/abs/10.1145/3197517.3201397),
+  [Symmetric Architecture](https://dl.acm.org/doi/abs/10.1145/3359566.3360070),
+  [Symmetric Data Augmentation](https://ieeexplore.ieee.org/abstract/document/10611493)
+
+## Cite
+
+If you find this framework useful for your research, please consider citing our work on legged locomotion:
+
+- [Efficient Learning of A Unified Policy For Whole-body Manipulation and Locomotion Skills](https://www.arxiv.org/abs/2507.04229), Accepted by IROS 2025
+- [Learning Accurate and Robust Velocity Tracking for Quadrupedal Robots](https://www.authorea.com/doi/full/10.22541/au.173321917.73583610), Accepted by JFR
+- [Learning Safe Locomotion for Quadrupedal Robots by Derived-Action Optimization](https://ieeexplore.ieee.org/abstract/document/10802725), Published in IROS 2024

cusrl-1.0.0/cusrl/__init__.py

@@ -0,0 +1,107 @@
+from cusrl import environment, hook, logger, module, preset, sampler, template, utils, zoo
+from cusrl.environment import make_gym_env, make_gym_vec, make_isaaclab_env
+from cusrl.module import (
+    CNN,
+    MLP,
+    RNN,
+    Actor,
+    AdaptiveNormalDist,
+    Denormalization,
+    Distribution,
+    DistributionFactoryLike,
+    FeedForward,
+    InferenceModule,
+    LayerFactoryLike,
+    Module,
+    ModuleFactory,
+    ModuleFactoryLike,
+    MultiheadSelfAttention,
+    NormalDist,
+    Normalization,
+    OneHotCategoricalDist,
+    Sequential,
+    Simba,
+    TransformerEncoderLayer,
+    Value,
+)
+from cusrl.sampler import (
+    AutoMiniBatchSampler,
+    MiniBatchSampler,
+    TemporalMiniBatchSampler,
+)
+from cusrl.template import (
+    ActorCritic,
+    Agent,
+    Buffer,
+    Environment,
+    EnvironmentSpec,
+    Hook,
+    Logger,
+    LoggerFactory,
+    LoggerFactoryLike,
+    OptimizerFactory,
+    Player,
+    Sampler,
+    Trainer,
+    Trial,
+)
+from cusrl.utils import (
+    device,
+    set_global_seed,
+)
+
+__all__ = [
+    "hook",
+    "logger",
+    "module",
+    "preset",
+    "sampler",
+    "template",
+    "utils",
+    "zoo",
+    "environment",
+    "Actor",
+    "ActorCritic",
+    "AdaptiveNormalDist",
+    "Agent",
+    "AutoMiniBatchSampler",
+    "Buffer",
+    "CNN",
+    "Denormalization",
+    "Distribution",
+    "DistributionFactoryLike",
+    "Environment",
+    "EnvironmentSpec",
+    "FeedForward",
+    "Hook",
+    "InferenceModule",
+    "LayerFactoryLike",
+    "Logger",
+    "LoggerFactory",
+    "LoggerFactoryLike",
+    "MLP",
+    "MiniBatchSampler",
+    "Module",
+    "ModuleFactory",
+    "ModuleFactoryLike",
+    "MultiheadSelfAttention",
+    "NormalDist",
+    "Normalization",
+    "OneHotCategoricalDist",
+    "OptimizerFactory",
+    "Player",
+    "RNN",
+    "Sampler",
+    "Sequential",
+    "Simba",
+    "TemporalMiniBatchSampler",
+    "Trainer",
+    "TransformerEncoderLayer",
+    "Trial",
+    "Value",
+    "device",
+    "make_gym_env",
+    "make_gym_vec",
+    "make_isaaclab_env",
+    "set_global_seed",
+]

cusrl-1.0.0/cusrl/environment/__init__.py

@@ -0,0 +1,11 @@
+from .gym import GymEnvAdapter, GymVectorEnvAdapter, make_gym_env, make_gym_vec
+from .isaaclab import IsaacLabEnvAdapter, make_isaaclab_env
+
+__all__ = [
+    "GymEnvAdapter",
+    "GymVectorEnvAdapter",
+    "IsaacLabEnvAdapter",
+    "make_gym_env",
+    "make_gym_vec",
+    "make_isaaclab_env",
+]