# UVIP: Model-Free Approach to Evaluate Reinforcement Learning Algorithms

arXiv: https://arxiv.org/abs/2105.02135 · HTML: https://mlsanity.com/paper/2105.02135/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 51 references that are in the map.
- First posted on arXiv 5 May 2021.

## Builds on (most cited first, 18 of 18)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [Minimax Regret Bounds for Reinforcement Learning](https://mlsanity.com/paper/1703.05449/) (2017)
- [Is Q-learning Provably Efficient?](https://mlsanity.com/paper/1807.03765/) (2018)
- [Learning Continuous Control Policies by Stochastic Value Gradients](https://mlsanity.com/paper/1510.09142/) (2015)
- [Policy Certificates: Towards Accountable Reinforcement Learning](https://mlsanity.com/paper/1811.03056/) (2018)
- [Variance-reduced Q-learning is minimax optimal](https://mlsanity.com/paper/1906.04697/) (2019)
- [A Comparative Analysis of Expected and Distributional Reinforcement Learning](https://mlsanity.com/paper/1901.11084/) (2019)
- [Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies](https://mlsanity.com/paper/1905.11527/) (2019)
- [Expected Policy Gradients for Reinforcement Learning](https://mlsanity.com/paper/1801.03326/) (2018)
- [Tightening Exploration in Upper Confidence Reinforcement Learning](https://mlsanity.com/paper/2004.09656/) (2020)
- [Kernel-Based Reinforcement Learning: A Finite-Time Analysis](https://mlsanity.com/paper/2004.05599/) (2020)
- [Practical Kernel-Based Reinforcement Learning](https://mlsanity.com/paper/1407.5358/) (2014)
- [Conditional Importance Sampling for Off-Policy Learning](https://mlsanity.com/paper/1910.07479/) (2019)
- [Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models](https://mlsanity.com/paper/1602.06346/) (2016)
- [Lookahead-Bounded Q-Learning](https://mlsanity.com/paper/2006.15690/) (2020)

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

- [Dual Approaches to Stochastic Control via SPDEs and the Pathwise Hopf Formula](https://mlsanity.com/paper/2604.08155/) (2026)

## Abstract (arXiv)

Policy evaluation is an important instrument for the comparison of different algorithms in Reinforcement Learning (RL). However, even a precise knowledge of the value function Vπ corresponding to a policy π does not provide reliable information on how far the policy π is from the optimal one. We present a novel model-free upper value iteration procedure (sf UVIP) that allows us to estimate the suboptimality gap Vstar(x) - Vπ(x) from above and to construct confidence intervals for (V^star). Our approach relies on upper bounds to the solution of the Bellman optimality equation via the martingale approach. We provide theoretical guarantees for sf UVIP under general assumptions and illustrate its performance on a number of benchmark RL problems.