Publication Radar · Source metadata
Optimal Value Inference for Reinforcement Learning
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-09-09 · Indexed by Pub-AI: 2026-10-31 UTC
Optimal Value Inference for Reinforcement Learning
Preprint posted: 2026-09-09 · Original record ↗
- arxiv
- 2609.09981
Explicit source versions (2)
- v3 · 2026-10-29
- v4 · 2026-11-03
- Explicit source version detected · v3
Source date: 2026-10-29 · First detected: 2026-10-31 UTC · Historical baseline
Source evidence (1)
- Official evidence ↗ · atom:id explicit version (official metadata)
- Preprint available
Source date: 2026-09-09 · First detected: 2026-10-31 UTC · Historical baseline
Source evidence (2)
- Official evidence ↗ · atom:published (official metadata)
- Official evidence ↗ · atom:published (official metadata)
- Explicit source version detected · v4
Source date: 2026-11-03 · First detected: 2026-11-13 UTC
Source evidence (1)
- Official evidence ↗ · atom:id explicit version (official metadata)
Abstract · arxiv
We study offline inference for the optimal value in reinforcement learning under finite state and action spaces. Two new nuisances are derived as fixed points of a self-induced Bellman equation, in which we approximate the maximum Bellman operator by its softmax correspondence. We propose a debiased estimator through the Neyman orthogonality and establish its asymptotic normality under diverging horizons even when the behavior policy changes with time, as long as the nuisances have the statistical rates that can be achieved by many machine learning methods. We provide a concrete estimating procedure for these nuisances and show they can lead to valid inference. Synthetic experiments validate the numerical performance of our inference method, and we implement it in real-life decision-making problems, including bike repositioning and AI agentic tool use.
