online-rl

[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training

🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

Open-source implementation of "RL Token: Bootstrapping Online RL with Vision-Language-Action Models"

[AAAI 2026] D²PPO: Diffusion Policy Policy Optimization with Dispersive Loss.

Official implementation of COST-HIL: Cost-Aware Human-in-the-Loop Reinforcement Learning for Real-World Dexterous Manipulation. This repo contains source codes, experiment logs, real-robot test scripts and supplementary materials for our CVPR submission.

Official implementation of HABC: Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes.

Pytorchを用いた強化学習のユースケース集(モデルフリー、モデルベース、オンライン学習、オフライン学習、世界モデル)

Online goal-reaching RL with diffusion planning: a 2D point-mass prototype plus a Maze2D Diffuser workflow driven by an autonomous agentic experiment controller.