论文标题
使用分形神经网络玩Simcity 1和Conway的生活游戏
Using Fractal Neural Networks to Play SimCity 1 and Conway's Game of Life at Variable Scales
论文作者
论文摘要
我们介绍了体育馆城市，这是一种增强学习环境，它使用Simcity 1的游戏引擎模拟城市环境，在该环境中，代理商可能会在各种尺寸的游戏板上优化任何数量的全市范围指标的一个或组合。我们专注于人群，并分析代理人比训练期间所看到的能力更大的地图大小。环境是互动的，使人类玩家在训练和推理过程中与代理商并肩作用，可能会影响他们的学习过程，或者手动探索和评估其表现。为了测试我们的代理商在游戏板元素之间捕获距离不足的关系的能力，我们在环境中设计了一个迷你游戏，而通过设计，在严格的本地策略下，通过设计不可分割。鉴于游戏引擎广泛使用蜂窝自动机，我们还训练代理商“玩”康威的生活游戏 - 再次为人口进行了优化 - 并以多个尺度检查其行为。为了使我们的模型与可变尺度的游戏玩法兼容，我们使用具有递归权重和结构的神经网络 - 分形在不同深度截断，取决于游戏板的大小。
We introduce gym-city, a Reinforcement Learning environment that uses SimCity 1's game engine to simulate an urban environment, wherein agents might seek to optimize one or a combination of any number of city-wide metrics, on gameboards of various sizes. We focus on population, and analyze our agents' ability to generalize to larger map-sizes than those seen during training. The environment is interactive, allowing a human player to build alongside agents during training and inference, potentially influencing the course of their learning, or manually probing and evaluating their performance. To test our agents' ability to capture distance-agnostic relationships between elements of the gameboard, we design a minigame within the environment which is, by design, unsolvable at large enough scales given strictly local strategies. Given the game engine's extensive use of Cellular Automata, we also train our agents to "play" Conway's Game of Life -- again optimizing for population -- and examine their behaviour at multiple scales. To make our models compatible with variable-scale gameplay, we use Neural Networks with recursive weights and structure -- fractals to be truncated at different depths, dependent upon the size of the gameboard.
