Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View

arXiv:2401.11237v2 Announce Type: replace
Abstract: Some reinforcement learning (RL) algorithms can stitch pieces of experience to solve a task never seen before during training. This oft-sought property is one of the few ways in which RL methods based on dynamic-programming differ from RL methods based on supervised-learning (SL). Yet, certain RL methods based on off-the-shelf SL algorithms achieve excellent results without an explicit mechanism for stitching; it remains unclear whether those methods forgo this important stitching property. This paper studies …

abstract algorithms arxiv cs.lg dynamic dynamic-programming experience gap programming property reinforcement reinforcement learning solve supervised learning training type view