RLinf is a flexible and scalable open-source RL infrastructure designed for Embodied and Agentic AI. The 'inf' in RLinf stands for Infrastructure, highlighting its role as a robust backbone for ...

Abstract: While reinforcement learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of ...

Abstract: Generative artificial intelligence has become the focus of the intelligent education field, especially in the generation of personalized learning resources. Current learning resource ...

Outcome-reward RL methods such as GRPO mainly learn from sparse trajectory-level success signals. EnvRL uses the richer interaction experience inside each rollout. Given a transition (history, obs_t, ...