# Tight Sample Complexity Bounds for Entropic Best Policy Identification

arXiv: https://arxiv.org/abs/2605.13717 · HTML: https://mlsanity.com/paper/2605.13717/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- Builds on 2 of its 30 references that are in the map.
- First posted on arXiv 13 May 2026.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Builds on (most cited first, 2 of 2)

- [Efficient Risk-sensitive Planning via Entropic Risk Measures](https://mlsanity.com/paper/2502.20423/) (2025)
- [Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model](https://mlsanity.com/paper/2506.00286/) (2025)

## Built on by (most cited first, 1 of 1)

- [Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model](https://mlsanity.com/paper/2610.06931/) (2026)

## Abstract (arXiv)

We study best-policy identification for finite-horizon risk-sensitive reinforcement learning under the entropic risk measure. Recent work established a constant gap in the exponential horizon dependence between lower and upper bounds on the number of samples required to identify an approximately optimal policy. Precisely, known lower bounds scale in Omega(e|β| H) where H is the horizon of the MDP, while the state-of-the-art upper bound achieves at best O(e2|β| H) (arXiv:2506.00286v2) using a generative model. We show that this extra exponential factor can be traced to overly loose concentration control for exponential utilities. To close this open gap, we revisit the analysis of this problem through a forward-model based algorithm building on KL-based exploration bonuses that we adapt to the entropic criterion. The improvement we get is due to two main novel technical innovations. We leverage the smoothness properties of the exponential utility to derive sharper concentration bounds, and we propose a new stopping rule that exploits further this tightness to obtain a sample complexity that matches the lower bound.