List your company

Average-reward Regret Minimization on Average-reward MDPs

1Regret BoundCorollary 3.6 (FOCUS)
0.950.97511.025Mar 25, 2026

Evaluation results

MethodLinks
Corollary 3.6 (FOCUS)Priorless?=×, Tractable?=✓, Type=UCB2026.031—