对抗最小化再次反击
Minimax Strikes Back
AI总结：
本文提出了一种基于Minimax的搜索算法Descent，通过不同的学习目标和不使用策略的方法，在多个游戏中比AlphaZero的重实现Polygames更高效，且在GPU资源更多时表现更优。
摘要：
深度强化学习在许多完全信息游戏中达到了超人类水平。当前零知识学习的最先进算法是AlphaZero。我们采取了另一种方法，Athénan，它使用了一种不同的基于Minimax的搜索算法Descent，以及不同的学习目标，并不使用策略。我们证明，在多个游戏中，Athénan比AlphaZero的重实现Polygames更高效。当Polygames使用100倍更多的GPU时，Athénan的表现甚至与之竞争（至少对于某些游戏）。Athénan性能优越的一个关键因素是生成训练状态数据的成本大约低296倍。在相同合理的资源下，不使用强化启发式的Athénan至少比Polygames快7倍，使用强化启发式时则快30倍以上。
英文摘要：
Deep Reinforcement Learning reaches a superhuman level of play in many complete information games. The state of the art algorithm for learning with zero knowledge is AlphaZero. We take another approach, Athénan, which uses a different, Minimax-based, search algorithm called Descent, as well as different learning targets and that does not use a policy. We show that for multiple games it is much more efficient than the reimplementation of AlphaZero: Polygames. It is even competitive with Polygames when Polygames uses 100 times more GPU (at least for some games). One of the keys to the superior performance is that the cost of generating state data for training is approximately 296 times lower with Athénan. With the same reasonable ressources, Athénan without reinforcement heuristic is at least 7 times faster than Polygames and much more than 30 times faster with reinforcement heuristic.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
