# AlphaViT: A flexible game-playing AI for multiple games and variable board sizes

arXiv: https://arxiv.org/abs/2408.13871 · HTML: https://mlsanity.com/paper/2408.13871/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 38 references that are in the map.
- First posted on arXiv 25 Aug 2024.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [Accelerating Self-Play Learning in Go](https://mlsanity.com/paper/1902.10565/) (2019)
- [Amortized Planning with Large-Scale Transformers: A Case Study on Chess](https://mlsanity.com/paper/2402.04494/) (2024)
- [A0C: Alpha Zero in Continuous Action Space](https://mlsanity.com/paper/1805.09613/) (2018)
- [Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers](https://mlsanity.com/paper/2304.14918/) (2023)
- [Multiplayer AlphaZero](https://mlsanity.com/paper/1910.13012/) (2019)
- [Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants](https://mlsanity.com/paper/2102.12375/) (2021)
- [Adaptive Warm-Start MCTS in AlphaZero-like Deep Reinforcement Learning](https://mlsanity.com/paper/2105.06136/) (2021)
- [Warm-Start AlphaZero Self-Play Search Enhancements](https://mlsanity.com/paper/2004.12357/) (2020)
- [AlphaDDA: Strategies for Adjusting the Playing Strength of a Fully Trained AlphaZero System to a Suitable Human Training Partner](https://mlsanity.com/paper/2111.06266/) (2021)
- [AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time](https://mlsanity.com/paper/2204.13307/) (2022)
- [An Evolutionary Framework for Connect-4 as Test-Bed for Comparison of Advanced Minimax, Q-Learning and MCTS](https://mlsanity.com/paper/2405.16595/) (2024)

## Abstract (arXiv)

We present three game-playing agents incorporating Vision Transformers (ViT) into the AlphaZero framework: AlphaViT, AlphaViD (AlphaViT with a transformer decoder), and AlphaVDA (AlphaViD with learnable action embeddings). These agents can play multiple board games of varying sizes using a single neural network with shared weights, thus overcoming AlphaZero's limitation of fixed board sizes. AlphaViT employs only a transformer encoder, whereas AlphaViD and AlphaVDA incorporate both a transformer encoder and a decoder. In AlphaViD, the decoder processes outputs from the encoder, whereas AlphaVDA uses learnable embeddings as the decoder inputs. The additional decoder in AlphaViD and AlphaVDA provides flexibility to adapt to various action spaces and board sizes. Experimental results show that the proposed agents, trained on either individual games or on multiple games simultaneously, consistently outperform traditional algorithms, such as Minimax and Monte Carlo Tree Search. They approach the performance of AlphaZero despite relying on a single deep neural network (DNN) with shared weights. In particular, AlphaViT performs strongly across all evaluated games. Furthermore, fine-tuning the DNN with weights pre-trained on small board games accelerates convergence and improves performance, particularly in Gomoku. Interestingly, simultaneous training on multiple games yields performance comparable to, or even surpassing, that of single-game training. These results indicate the potential of transformer-based architectures for developing more flexible and robust game-playing AI agents that excel in multiple games and dynamic environments.