# Improving Robustness of AlphaZero Algorithms to Test-Time Environment Changes

arXiv: https://arxiv.org/abs/2509.04317 · HTML: https://mlsanity.com/paper/2509.04317/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 4 Sep 2025.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [Are AlphaZero-like Agents Robust to Adversarial Perturbations?](https://mlsanity.com/paper/2211.03769/) (2022)
- [Monte Carlo Tree Search for Asymmetric Trees](https://mlsanity.com/paper/1805.09218/) (2018)
- [Decision Making in Non-Stationary Environments with Policy-Augmented Search](https://mlsanity.com/paper/2401.03197/) (2024)
- [Brick Tic-Tac-Toe: Exploring the Generalizability of AlphaZero to Novel Test Environments](https://mlsanity.com/paper/2207.05991/) (2022)

## Abstract (arXiv)

The AlphaZero framework provides a standard way of combining Monte Carlo planning with prior knowledge provided by a previously trained policy-value neural network. AlphaZero usually assumes that the environment on which the neural network was trained will not change at test time, which constrains its applicability. In this paper, we analyze the problem of deploying AlphaZero agents in potentially changed test environments and demonstrate how the combination of simple modifications to the standard framework can significantly boost performance, even in settings with a low planning budget available. The code is publicly available on GitHub.