Offline Reinforcement Learning with Behavioral Supervisor Tuning

arXiv:2404.16399v1 Announce Type: new
Abstract: Offline reinforcement learning (RL) algorithms are applied to learn performant, well-generalizing policies when provided with a static dataset of interactions. Many recent approaches to offline RL have seen substantial success, but with one key caveat: they demand substantial per-dataset hyperparameter tuning to achieve reported performance, which requires policy rollouts in the environment to evaluate; this can rapidly become cumbersome. Furthermore, substantial tuning requirements can hamper the adoption of these algorithms in practical domains. In this …

abstract algorithms arxiv cs.ai cs.lg dataset demand hyperparameter interactions key learn offline per performance policies policy reinforcement reinforcement learning success type