Papers › UVIP: Model-Free Approach to Evaluate Reinforcement Learning Algorithms
UVIP: Model-Free Approach to Evaluate Reinforcement Learning Algorithms
Ilya Levin, Denis Belomestny, Alexey Naumov, Sergey Samsonov
Policy evaluation is an important instrument for the comparison of different algorithms in Reinforcement Learning (RL). Yet even a precise knowledge of the value function V^π corresponding to a policy π does not provide reliable information on how far is the policy π from the optimal one. We present a novel model-free upper value iteration procedure (UVIP) that allows us to estimate the suboptimality gap V^⋆(x) - V^π(x) from above and to construct confidence intervals for V^⋆. Our approach relies on upper bounds to the solution of the Bellman optimality equation via martingale approach. We provide theoretical guarantees for UVIP under general assumptions and illustrate its performance on a number of benchmark RL problems.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections