4 papers
Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation
Xinyao Qin, Junjie Lu, Kaixin Wang +7
Human demonstrations for robot imitation learning often contain mistakes and corrective behaviors, such as imprecise grasps, object misalignment, unstable contact, and repeated att…
SEAGym: An Evaluation Environment for Self-Evolving LLM Agents
Congjie Zheng, Chuanyi Xue, Bin Liang +2
Self-evolving LLM-based agents improve mainly by changing their agent harness: the structured execution layer around a base model, including prompts, memory, tools, middleware, run…
Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning
Ziyu Cheng, Jinsheng Ren, Zhouxian Jiang +4
Effective communication is pivotal for addressing complex collaborative tasks in multi-agent reinforcement learning (MARL). Yet, limited communication bandwidth and dynamic, intric…
Integrating Diffusion-based Multi-task Learning with Online Reinforcement Learning for Robust Quadruped Robot Control
Xinyao Qin, Xiaoteng Ma, Yang Qi +6
Recent research has highlighted the powerful capabilities of imitation learning in robotics. Leveraging generative models, particularly diffusion models, these approaches offer not…