APC-MGE by Schneider Electric, O'Fallon, MO 63368, USA.
Neural Netw. 2010 Mar;23(2):295-305. doi: 10.1016/j.neunet.2009.11.001. Epub 2009 Nov 20.
Evaluation of the current board position is critical in computer game engines. In sufficiently complex games, such a task is too difficult for a traditional brute force search to accomplish, even when combined with expert knowledge bases. This motivates the investigation of alternatives. This paper investigates the combination of neural networks, particle swarm optimization (PSO), and evolutionary algorithms (EAs) to train a board evaluator from zero knowledge. By enhancing the survivors of an EA with PSO, the hybrid algorithm successfully trains the high-dimensional neural networks to provide an evaluation of the game board through self-play. Experimental results, on the benchmark game of Capture Go, demonstrate that the hybrid algorithm can be more powerful than its individual parts, with the system playing against EA and PSO trained game engines. Also, the winning results of tournaments against a Hill-Climbing trained game engine confirm that the improvement comes from the hybrid algorithm itself. The hybrid game engine is also demonstrated against a hand-coded defensive player and a web player.
在电脑游戏引擎中，评估当前的董事会职位是至关重要的。在足够复杂的游戏中，即使结合了专家知识库，传统的暴力搜索也很难完成这样的任务。这促使人们寻求替代方案。本文研究了神经网络、粒子群优化（PSO）和进化算法（EAs）的组合，以从零知识开始训练董事会评估器。通过使用 PSO 增强 EA 的幸存者，混合算法成功地训练了高维神经网络，通过自我博弈为游戏板提供评估。在基准游戏 Capture Go 上的实验结果表明，混合算法可以比其各个部分更强大，系统可以与 EA 和 PSO 训练的游戏引擎进行对抗。此外，与 Hill-Climbing 训练的游戏引擎进行的锦标赛的获胜结果证实，改进来自于混合算法本身。混合游戏引擎还针对手动编码的防御球员和网络玩家进行了演示。
