# Combining No-regret and Q-learning

arXiv: https://arxiv.org/abs/1910.03094 · HTML: https://mlsanity.com/paper/1910.03094/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2019.

## Built on by (most cited first, 4 of 4)

- [The Confluence of Networks, Games and Learning](https://mlsanity.com/paper/2105.08158/) (2021)
- [Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games](https://mlsanity.com/paper/2102.06973/) (2021)
- [Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games](https://mlsanity.com/paper/2103.04539/) (2021)
- [Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games: Corrections](https://mlsanity.com/paper/2205.12031/) (2022)

## Abstract (arXiv)

Counterfactual Regret Minimization (CFR) has found success in settings like poker which have both terminal states and perfect recall. We seek to understand how to relax these requirements. As a first step, we introduce a simple algorithm, local no-regret learning (LONR), which uses a Q-learning-like update rule to allow learning without terminal states or perfect recall. We prove its convergence for the basic case of MDPs (and limited extensions of them) and present empirical results showing that it achieves last iterate convergence in a number of settings, most notably NoSDE games, a class of Markov games specifically designed to be challenging to learn where no prior algorithm is known to achieve convergence to a stationary equilibrium even on average.