skrl
RL library
A modular reinforcement learning library with support for various environments and frameworks
Modular reinforcement learning library (on PyTorch and JAX) with support for NVIDIA Isaac Gym, Omniverse Isaac Gym and Isaac Lab
588 stars
9 watching
61 forks
Language: Python
last commit: about 2 months ago
Linked from 2 awesome lists
deep-learningdeepmindgymgymnasiumisaac-gymisaac-labisaac-orbitisaac-simisaaclabjaxmachine-learningnvidia-omniverseopenai-gympythonpytorchreinforcement-learningrlrobosuiteroboticsskrl
ethicalml/awesome-production-machine-learning
krzjoa/awesome-python-data-scienceRelated projects:
| Repository | Description | Stars |
|---|---|---|
 matthiasplappert/keras-rl | A Python library implementing state-of-the-art deep reinforcement learning algorithms for Keras and OpenAI Gym environments. | 8 |
 mushroomrl/mushroom-rl | A Python library for reinforcement learning algorithms and environments. | 824 |
 luchris429/purejaxrl | A high-performance implementation of reinforcement learning training pipelines using JAX and PyTorch-like functionality | 755 |
 ikostrikov/jaxrl | Provides JAX implementations of various reinforcement learning algorithms with continuous action spaces. | 640 |
 rl-tools/rl-tools | An open-source C++ library for training reinforcement learning policies and controlling continuous-control environments. | 680 |
 alex-petrenko/sample-factory | A high-throughput reinforcement learning library with optimized synchronous and asynchronous implementations of policy gradients. | 839 |
 tristandeleu/pytorch-maml-rl | Replication of Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks in PyTorch for reinforcement learning tasks | 830 |
 sjtu-marl/malib | A framework for parallel population-based reinforcement learning | 507 |
 takuseno/d3rlpy | An open-source deep reinforcement learning library that supports offline and online training, providing an intuitive API for practitioners and researchers. | 1,349 |
 corl-team/corl | Provides high-quality implementations of offline and offline-to-online reinforcement learning algorithms in Python. | 491 |
 volcengine/verl | A flexible RL training framework designed for large language models | 427 |
 kaixhin/rainbow | A Python implementation of a deep reinforcement learning algorithm combining multiple techniques for improved performance in Atari games | 1,591 |
 iffix/machin | An open-source reinforcement learning library for PyTorch, providing a simple and clear implementation of various algorithms. | 402 |
 enlite-ai/maze | An RL framework for building and training reinforcement learning models in Python | 266 |
 rle-foundation/rlexplore | Provides a unified toolkit for constructing, computing, and optimizing intrinsic reward modules in reinforcement learning | 373 |