RUC-NLPIR/ARPO

[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)

agentic-rlreinforcement-learningreinforcement-learning-agentreinforcement-learning-algorithmsrl

License & maintenance

No license stated: by default nobody may reuse the code. Ask the authors before using it in a product.

Last code push 8 days ago.

	Repository	Stars	Language	License	Activity
1	Unity-Technologies/ml-agentsThe Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments	★ 19.8k	C#	Other	Active
2	tensorflow/tensor2tensorLibrary of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.	★ 17.5k	Python	Apache-2.0	Archived
3	owainlewis/awesome-artificial-intelligenceA curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.	★ 16.7k	Python	MIT	Active
4	bulletphysics/bullet3Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc	★ 14.8k	C++	Other	Active
5	ShangtongZhang/reinforcement-learning-an-introductionPython Implementation of Reinforcement Learning: An Introduction	★ 14.8k	Python	MIT	Stale
6	Farama-Foundation/GymnasiumA standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym	★ 12.7k	Python	MIT	Active
7	aws/amazon-sagemaker-examplesExample 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.	★ 11k	Jupyter Notebook	Apache-2.0	Active
8	google/dopamineDopamine is a research framework for fast prototyping of reinforcement learning algorithms.	★ 10.9k	Jupyter Notebook	Apache-2.0	Slowing