On Practical Robust Reinforcement Learning: Adjacent Uncertainty Set and Double-Agent Algorithm

• Published in: IEEE transaction on neural networks and learning systems Vol. 36; no. 4; pp. 7696 - 7710
• Main Authors: Hwang, Ukjo, Hong, Songnam
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2025
• Subjects: Optimization; Q-learning; Reinforcement learning (RL); robust RL (RRL); Robustness; Testing; Training; Uncertainty; uncertainty set

Robust reinforcement learning (RRL) aims to seek a robust policy by optimizing the worst case performance over an uncertainty set. This set contains some perturbed Markov decision processes (MDPs) from a nominal MDP (N-MDP) that generate samples for training, which reflects some potential mismatches...