SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation

arXiv:2403.00991v1 Announce Type: cross
Abstract: Autonomous self-improving robots that interact and improve with experience are key to the real-world deployment of robotic systems. In this paper, we propose an online learning method, SELFI, that leverages online robot experience to rapidly fine-tune pre-trained control policies efficiently. SELFI applies online model-free reinforcement learning on top of offline model-based learning to bring out the best parts of both learning paradigms. Specifically, SELFI stabilizes the online learning process by incorporating the same model-based learning …

abstract arxiv autonomous control cs.cv cs.lg cs.ro deployment experience free improvement key navigation online learning paper reinforcement reinforcement learning robot robotic robots self-improvement social systems type world