The authors derive a finite-sample adaptive-data performance bound for FQI by chaining measure-theoretic probability with Bellman contractions and prove the first cumulative pathwise online regret guarantee in continuous spaces using sequential Rademacher complexity.
Minimax regret bounds for reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Measure-Theoretic Finite-Sample Theory for Adaptive-Data Fitted Q-Iteration
The authors derive a finite-sample adaptive-data performance bound for FQI by chaining measure-theoretic probability with Bellman contractions and prove the first cumulative pathwise online regret guarantee in continuous spaces using sequential Rademacher complexity.