Out-of-Distribution Adaptation in Offline RL: Counterfactual Reasoning via Causal Normalizing Flows

arXiv:2405.03892v1 Announce Type: new
Abstract: Despite notable successes of Reinforcement Learning (RL), the prevalent use of an online learning paradigm prevents its widespread adoption, especially in hazardous or costly scenarios. Offline RL has emerged as an alternative solution, learning from pre-collected static datasets. However, this offline learning introduces a new challenge known as distributional shift, degrading the performance when the policy is evaluated on scenarios that are Out-Of-Distribution (OOD) from the training dataset. Most existing offline RL resolves this issue …

abstract adoption alternative arxiv causal counterfactual cs.ai cs.lg datasets distribution however offline online learning paradigm reasoning reinforcement reinforcement learning solution type via