Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics
-
Updated
Oct 28, 2026 - Python
Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics
A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).
A collection of Reinforcement Learning GitHub code resources divided by frameworks and environments
[NeurIPS 2026] FedAgent: A Library for Decentralized Agent Learning. 🏆 Best Paper Award at the AAAI'26 TrustAgent Workshop, 🏆 Outstanding Paper Award in the AAAI'26 PerFM Workshop.
Tensor-Optix is an adaptive ML and RL framework that simplifies model development through intelligent optimisation, automated training, neuroevolution and experiment management, giving developers more power with less complexity.
PyTorch reimplementation of "Deep Hierarchical Planning" RL framework. Features a multi-model architecture with manager-worker policies, world model, and goal autoencoder. Built with Python/PyTorch and includes experiment logging with Weights & Biases.
Practical Agentic AI and RAG Course
A pure Rust Reinforcement Learning framework featuring a custom tensor engine, autograd system, and modular RL algorithms.
To associate your repository with the rl-framework topic, visit your repo's landing page and select "manage topics."