arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.10391cs.LGstat.ML
收藏

用于高级字符控制的深度强化学习

Deep Reinforcement Learning for High Level Character Control

Instituto Nacional de Matemática Pura e Aplicada(国家纯数学与应用数学研究所)

Caio Souza, Luiz Velho

摘要:

在本文中,我们提出了使用传统的动画,启发式行为和强化学习在创造智能字符的计算媒体。传统的动画和启发式方法对行为进行艺术控制,而强化学习则增加了泛化。所呈现的用例是一个在3D环境中具有高级控制器的狗角色,该环境是围绕要学习的期望行为(例如获取物品)构建的。由于环境的发展是学习的关键,进一步分析了如何建立这些学习环境,环境和代理模型的选择,训练过程和学习行为的泛化的影响进行。这种分析建立了对上述因素的洞察力,并可作为一般环境发展的指导。

英文摘要:

In this paper, we propose the use of traditional animations, heuristic behavior and reinforcement learning in the creation of intelligent characters for computational media. The traditional animation and heuristic gives artistic control over the behavior while the reinforcement learning adds generalization. The use case presented is a dog character with a high-level controller in a 3D environment which is built around the desired behaviors to be learned, such as fetching an item. As the development of the environment is the key for learning, further analysis is conducted of how to build those learning environments, the effects of environment and agent modeling choices, training procedures and generalization of the learned behavior. This analysis builds insight of the aforementioned factors and may serve as guide in the development of environments in general.

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。

↑