Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions
- Resource Type
- Working Paper
- Authors
- Li, Tongxin; Lin, Yiheng; Ren, Shaolei; Wierman, Adam
- Source
- Subject
- Computer Science - Machine Learning
Computer Science - Performance
- Language
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.
Comment: 32 pages, NeurIPS 2023