Libraries & frameworks
relax
redai-infra/relax
Large-scale asynchronous reinforcement learning engine for omni-modal model post-training, decoupling training from inference while supporting elastic scaling across distributed resources.
Topics
Related projects
verl-omni1.5kA reinforcement learning training framework for diffusion and omni-modal generative models built on VeRL.
hands-on-modern-rl4.9kAn open hands-on curriculum covering classical reinforcement learning through LLM alignment, RLVR, and agentic systems with runnable experiments.
OSWorld3.3kOSWorld is a benchmark and real desktop environment for evaluating multimodal computer-use agents, with support for VMware, Docker, AWS, and other backends for reproducible task evaluation.
pytorch-image-models37.3kA large PyTorch image-model library with backbones, pretrained weights, training scripts, and utilities for vision research.
Paddle24.1kBaidu's PaddlePaddle deep learning framework for high-performance single-node, distributed training, and deployment.
ml-agents19.9kUnity's open toolkit for training intelligent game agents with deep reinforcement and imitation learning through Python and Unity APIs.