Can I read MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games on EtoBox?

MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games by Wu, Ti-Rong; Guei, Hung; Peng, Pei-Chiun; Huang, Po-Wei; Wei, Ting Han; Shih, Chung-Chin; Tsai, Yun-Jui is a scholarly article available to read on EtoBox.

What is MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games about?

This paper presents MiniZero, a zero-knowledge learning framework that supports four state-of-the-art algorithms, including AlphaZero, MuZero, Gumbel AlphaZero, and Gumbel MuZero. While these algorithms have demonstrated super-human performance in many games, it remains unclear which among them is most suitable or efficient for specific tasks. Through MiniZero, we systematically evaluate the performance of each algorithm in two board games, 9x9 Go and 8x8 Othello, as well as 57 Atari games. For two board games, using more simulations generally results in higher performance. However, the choice of AlphaZero and MuZero may differ based on game properties. For Atari games, both MuZero and Gumbel MuZero are worth considering. Since each game has unique characteristics, different algorithms and simulations yield varying results. In addition, we introduce an approach, called progressive simulation, which progressively increases the simulation budget during training to allocate computation more efficiently. Our empirical results demonstrate that progressive simulation achieves significantly superior performance in two board games. By making our framework and trained models publicly availa

Author

Wu, Ti-Rong; Guei, Hung; Peng, Pei-Chiun; Huang, Po-Wei; Wei, Ting Han; Shih, Chung-Chin; Tsai, Yun-Jui

Published

2023

Language

EN