2 papers
cs.RO2025
Unlock Reliable Skill Inference for Quadruped Adaptive Behavior by Skill Graph
Hongyin Zhang, Diyuan Shi, Zifeng Zhuang +6
Developing robotic intelligent systems that can adapt quickly to unseen wild situations is one of the critical challenges in pursuing autonomous robotics. Although some impressive…
cs.LG2024
Data-Incremental Continual Offline Reinforcement Learning
Sibo Gai, Donglin Wang
In this work, we propose a new setting of continual learning: data-incremental continual offline reinforcement learning (DICORL), in which an agent is asked to learn a sequence of…