Hybrid Inverse Reinforcement Learning

arXiv:2402.08848v1 Announce Type: new
Abstract: The inverse reinforcement learning approach to imitation learning is a double-edged sword. On the one hand, it can enable learning from a smaller number of expert demonstrations with more robustness to error compounding than behavioral cloning approaches. On the other hand, it requires that the learner repeatedly solve a computationally expensive reinforcement learning (RL) problem. Often, much of this computation is wasted searching over policies very dissimilar to the expert's. In this work, we propose …

abstract arxiv cloning cs.ai cs.lg error expert hybrid imitation learning reinforcement reinforcement learning robustness solve type