arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.01153cs.NE
收藏

使用MAP-Elites对环境及适配智能体进行开放式搜索

Open-ended search for environments and adapted agents using MAP-Elites

Emma Stensby Norstein, Kai Olav Ellefsen, Kyrre Glette

AI总结:

本研究借助MAP-Elites构建含地形与适配虚拟生物的结构化开放式搜索地图,结合新颖性维度实现无边界探索,验证了有界与无界方法均可解决多样地形任务,推动类现实多样模拟环境构建。

摘要:

现实世界中的生物会不断遭遇前所未见的全新多样挑战,它们通常需要适应其中部分任务并加以解决才能生存。这种近乎无穷无尽的新奇挑战场景在虚拟环境中并不常见,人工进化的智能体在虚拟环境里往往只有有限的待解决任务集。开放式演化领域是个例外,其目标是实现对有趣人工产物的无边界探索。我们希望向创建类似多样现实世界的模拟环境再迈进一步,让智能体既能找到可解任务,又能适应这些任务。我们借助MAP-Elites(一种质量多样性算法)构建了一个结构化的技能库,也就是一张包含地形以及在地形中移动的虚拟生物的地图。通过将新颖性作为网格中的一个维度,该地图可以持续演化,推动对新环境的探索。智能体必须适应所发现的环境,但也可以在网格的每个单元内搜索环境,以找到最契合自身技能集的环境。我们的方法将MAP-Elites的结构化特性与开放式创新相结合,前者能让虚拟生物以相邻单元为垫脚石,解决难度逐步提升的环境问题,这种结合带来了一种无边界但仍具备清晰结构的搜索模式。我们发现,尽管为地图手工设计的有界维度能更快探索大量环境,但有界方法和无界方法都能成功解决多样化的地形任务。

英文摘要:

Creatures in the real world constantly encounter new and diverse challenges they have never seen before. They will often need to adapt to some of these tasks and solve them in order to survive. This almost endless world of novel challenges is not as common in virtual environments, where artificially evolving agents often have a limited set of tasks to solve. An exception to this is the field of open-endedness where the goal is to create unbounded exploration of interesting artefacts. We want to move one step closer to creating simulated environments similar to the diverse real world, where agents can both find solvable tasks, and adapt to them. Through the use of MAP-Elites we create a structured repertoire, a map, of terrains and virtual creatures that locomote through them. By using novelty as a dimension in the grid, the map can continuously develop to encourage exploration of new environments. The agents must adapt to the environments found, but can also search for environments within each cell of the grid to find the one that best fits their set of skills. Our approach combines the structure of MAP-Elites, which can allow the virtual creatures to use adjacent cells as stepping stones to solve increasingly difficult environments, with open-ended innovation. This leads to a search that is unbounded, but still has a clear structure. We find that while handcrafted bounded dimensions for the map lead to quicker exploration of a large set of environments, both the bounded and unbounded approach manage to solve a diverse set of terrains.

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。

↑