Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption

arXiv:2402.08991v1 Announce Type: cross
Abstract: This study tackles the challenges of adversarial corruption in model-based reinforcement learning (RL), where the transition dynamics can be corrupted by an adversary. Existing studies on corruption-robust RL mostly focus on the setting of model-free RL, where robust least-square regression is often employed for value function estimation. However, these techniques cannot be directly applied to model-based RL. In this paper, we focus on model-based RL and take the maximum likelihood estimation (MLE) approach to learn …

abstract adversarial arxiv challenges corruption cs.lg dynamics focus free function least regression reinforcement reinforcement learning robust square stat.ml studies study transition type value