Skip to yearly menu bar Skip to main content


Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions

Tongxin Li · Yiheng Lin · Shaolei Ren · Adam Wierman

Great Hall & Hall B1+B2 (level 1) #1901
[ ]
[ Paper [ Poster [ OpenReview
Wed 13 Dec 3 p.m. PST — 5 p.m. PST


We study the tradeoff between consistency and robustness in the context of a single-trajectory time-varying Markov Decision Process (MDP) with untrusted machine-learned advice. Our work departs from the typical approach of treating advice as coming from black-box sources by instead considering a setting where additional information about how the advice is generated is available. We prove a first-of-its-kind consistency and robustness tradeoff given Q-value advice under a general MDP model that includes both continuous and discrete state/action spaces. Our results highlight that utilizing Q-value advice enables dynamic pursuit of the better of machine-learned advice and a robust baseline, thus result in near-optimal performance guarantees, which provably improves what can be obtained solely with black-box advice.

Chat is not available.