method · first seen 22 Oct 2026
adversarial linear Markov decision process
Also: adversarial linear MDP
Reinforcement learning setting with linear transitions and adversarially chosen losses under bandit feedback.
Mentions per week
PapersCodeDiscussion
Earliest sources
- A Computationally Efficient and Rate-Optimal Algorithm for Adversarial Linear MDPs with (Aggregate) Bandit FeedbackPapers · 22 Oct 2026 · Haolin Liu, Chen-Yu Wei, Hanbin Zhou
Latest sources
- A Computationally Efficient and Rate-Optimal Algorithm for Adversarial Linear MDPs with (Aggregate) Bandit FeedbackPapers · 22 Oct 2026 · Haolin Liu, Chen-Yu Wei, Hanbin Zhou