PARL
RL framework
A high-performance distributed training framework for Reinforcement Learning
A high-performance distributed training framework for Reinforcement Learning
3k stars
63 watching
818 forks
Language: Python
last commit: 7 months ago
Linked from 2 awesome lists
large-scaleparallelizationreinforcement-learning
ethicalml/awesome-production-machine-learning
tigerneil/awesome-deep-rlRelated projects:
| Repository | Description | Stars |
|---|---|---|
| paddlepaddle/paddle | A high-performance deep learning framework designed for industrial-scale training and deployment of neural networks. | 22,340 |
 vwxyzjn/cleanrl | A single-file implementation of Deep Reinforcement Learning algorithms with research-friendly features. | 5,891 |
 carperai/trlx | A framework for distributed reinforcement learning of large language models with human feedback | 4,537 |
 kunqian2025/reinforcement-learning | A collection of implementations of reinforcement learning algorithms in MATLAB | 61 |
 tju-drl-lab/ai-optimizer | A next-generation deep reinforcement learning toolkit with libraries for multiagent, self-supervised, offline, and transfer/reinforcement learning | 4,848 |
 luchris429/purejaxrl | A high-performance implementation of reinforcement learning training pipelines using JAX and PyTorch-like functionality | 755 |
 rlcode/reinforcement-learning | A collection of clean and minimal examples for various reinforcement learning algorithms | 3,433 |
 sjtu-marl/malib | A framework for parallel population-based reinforcement learning | 507 |
 replicable-marl/marllib | A comprehensive platform for developing and testing Multi-agent Reinforcement Learning algorithms in various tasks and environments. | 960 |
 yandexdataschool/practical_rl | An educational resource teaching practical reinforcement learning skills in Python using popular deep learning frameworks. | 5,952 |
 huggingface/trl | A library designed to train transformer language models with reinforcement learning using various optimization techniques and fine-tuning methods. | 10,308 |
| paddlepaddle/paddlefl | A framework that enables secure and efficient distributed machine learning across multiple organizations without sharing raw data. | 499 |
 iffix/machin | An open-source reinforcement learning library for PyTorch, providing a simple and clear implementation of various algorithms. | 402 |
 hubfire/muti-branch-ddpg-carla | An implementation of a reinforcement learning algorithm using multi-branch architecture and Deep Deterministic Policy Gradients (DDPG) to control autonomous vehicles in simulation environments. | 81 |
 alex-petrenko/sample-factory | A high-throughput reinforcement learning library with optimized synchronous and asynchronous implementations of policy gradients. | 839 |