Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts

arXiv:2402.09992v1 Announce Type: new
Abstract: We study the robustness of deep reinforcement learning algorithms against distribution shifts within contextual multi-stage stochastic combinatorial optimization problems from the operations research domain. In this context, risk-sensitive algorithms promise to learn robust policies. While this field is of general interest to the reinforcement learning community, most studies up-to-date focus on theoretical results rather than real-world performance. With this work, we aim to bridge this gap by formally deriving a novel risk-sensitive deep reinforcement learning …

abstract actor actor-critic algorithms arxiv context cs.lg cs.sy distribution domain eess.sy general learn operations optimization reinforcement reinforcement learning research risk robust robustness stage stochastic study type