Evolving a Non-playable Character team with Layered Learning
Evolving a Non-playable Character team with Layered Learning
复制标题
通过分层学习发展不可玩角色团队
DOI：
10.1109/smdcm.2011.5949283
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
R. P. Wiegand
中科院分区：
文献类型：
--
作者：
Sean C. Mondesire;R. P. Wiegand
分层学习是一种迭代机器学习技术，用于训练代理如何执行任务。该技术将任务分解为更简单的组件，并训练代理学习如何执行更复杂的子任务来解决整个任务。分层学习已经成功地用于指导计算机程序解决布尔逻辑问题，教机器人如何走路，训练RoboCup足球代理。所提出的工作回答了分层学习如何适用于视频游戏中的非可玩角色（NPC）的异构团队的进化发展的问题。这项工作比较了分层学习的使用对发展中的NPC与单片为基础的方法。实验数据表明，分层学习可以成功地开发NPC，并证明了该方法表现出良好的整体评价。
Layered Learning is an iterative machine learning technique used to train agents how to perform tasks. The technique decomposes a task into simpler components and trains the agent to learn how to perform progressively more complex sub-tasks to solve the overall task. Layered Learning has been successfully used to instruct computer programs to solve Boolean-logic problems, teach robots how to walk, and train RoboCup soccer playing agents. The proposed work answers the question of how well does Layered Learning apply to the evolved development of a heterogeneous team of Non-playable Characters (NPCs) in a video game. The work compares the use of Layered Learning against evolving NPCs with monolithic based approaches. Experiment data show that Layered Learning can result in the successful development of NPCs and demonstrates that the approach performs well against monolithic evaluation.