arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.07579cs.AIcs.GRcs.LG
收藏

空间组装:基于强化学习、自玩和树搜索的生成式建筑

Spatial Assembly: Generative Architecture With Reinforcement Learning, Self Play and Tree Search

University of Oxford(牛津大学);Bartlett School of Architecture, UCL(伦敦大学学院巴特莱特建筑学院)

Panagiotis Tigas, Tyson Hosmer

摘要:

在这项工作中,我们研究了使用强化学习(RL)的空间组件的生成,通过结合程序生成算法(波函数折叠算法(WFC))和RL的游戏解决的想法。WFC是一种生成式设计算法,受约束求解的启发。在WFC中,定义了一组瓦片/块和约束,并且算法生成满足这些约束的组件。将空间装配体的生成问题转化为一个马尔可夫决策过程,其状态转移由WFC定义,提出了一种利用强化学习和Self-Play学习策略生成装配体的算法,该算法能够最大化设计者设定的目标。最后,我们展示了我们的空间组装算法在建筑设计中的应用。

英文摘要:

With this work, we investigate the use of Reinforcement Learning (RL) for the generation of spatial assemblies, by combining ideas from Procedural Generation algorithms (Wave Function Collapse algorithm (WFC)) and RL for Game Solving. WFC is a Generative Design algorithm, inspired by Constraint Solving. In WFC, one defines a set of tiles/blocks and constraints and the algorithm generates an assembly that satisfies these constraints. Casting the problem of generation of spatial assemblies as a Markov Decision Process whose states transitions are defined by WFC, we propose an algorithm that uses Reinforcement Learning and Self-Play to learn a policy that generates assemblies that maximize objectives set by the designer. Finally, we demonstrate the use of our Spatial Assembly algorithm in Architecture Design.

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。

↑