2 papers
cs.RO2026
Accelerating Robotic Reinforcement Learning with Agent Guidance
Haojun Chen, Zili Zou, Chengdong Ma +4
Reinforcement Learning (RL) offers a powerful paradigm for autonomous robots to master generalist manipulation skills through trial-and-error. However, its real-world application i…
cs.CL2024
Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge
Haotong Zhang
We carry out a series of experiments to test large language models' multi-hop reasoning ability from three aspects: selecting and combining external knowledge, dealing with non-seq…