Humans possess a remarkable balance between stability and flexibility, enabling them to quickly establish new plans and ...

Note: The official code and model weights are now available! Please star ⭐ this repository to stay updated. Doctor-R1 is an AI doctor agent trained to conduct strategic, multi-turn patient inquiries ...

Abstract: To address the critical challenges of multi-agent reinforcement learning under human interactive inputs, this paper proposes a novel robust and interpretable reinforcement learning framework ...