Paradox of AlphaZero: Strategic vs. Optimal Plays
2020 IEEE 39th International Performance Computing and Communications Conference (IPCCC)(2020)
摘要
This article analyzes AlphaZero-type algorithms quantitatively from the viewpoint of local and global optimal sequences of play on a 7×7 board. Through targeted evaluation of the AI agent, the authors reveal the strategic, that is, winrate-dominated, nature of such algorithms, and expose thereby certain inherent obstacles against optimal play. Possible remedies are then explored, leading to techniques that may help further quantitative analysis of those algorithms and for the search for optimal solutions, on 7×7 as well as larger boards.
更多查看译文
关键词
Game of Go,artificial intelligence,AlphaZero,optimal play,targeted evaluation,targeted training
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要