# AsyncQVI: Asynchronous-Parallel Q-Value Iteration for Discounted Markov Decision Processes with Near-Optimal Sample Complexity

arXiv: https://arxiv.org/abs/1812.00885 · HTML: https://mlsanity.com/paper/1812.00885/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2018.

## Built on by (most cited first, 3 of 3)

- [Asynchronous Iterations in Optimization: New Sequence Results and Sharper Algorithmic Guarantees](https://mlsanity.com/paper/2109.04522/) (2021)
- [Accelerating Value Iteration with Anchoring](https://mlsanity.com/paper/2305.16569/) (2023)
- [Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions](https://mlsanity.com/paper/2207.01613/) (2022)

## Abstract (arXiv)

In this paper, we propose AsyncQVI, an asynchronous-parallel Q-value iteration for discounted Markov decision processes whose transition and reward can only be sampled through a generative model. Given such a problem with |S| states, |A| actions, and a discounted factor γ∈(0,1), AsyncQVI uses memory of size O(|S|) and returns an varepsilon-optimal policy with probability at least 1-δ using tildeObig(frac|S||A|(1-γ)5varepsilon2log(frac1δ)big) samples. AsyncQVI is also the first asynchronous-parallel algorithm for discounted Markov decision processes that has a sample complexity, which nearly matches the theoretical lower bound. The relatively low memory footprint and parallel ability make AsyncQVI suitable for large-scale applications. In numerical tests, we compare AsyncQVI with four sample-based value iteration methods. The results show that our algorithm is highly efficient and achieves linear parallel speedup.