cs.AI updates on arXiv.org 5小时前
Learning telic-controllable state representations
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出一种在有限智能体中学习状态表示的框架,强调描述与规范性在目标导向状态下的耦合,并引入telic-controllability概念,以平衡目标灵活性与认知复杂性。

arXiv:2406.14476v3 Announce Type: replace Abstract: Computational models of purposeful behavior comprise both descriptive and prescriptive aspects, used respectively to ascertain and evaluate situations in the world. In reinforcement learning, prescriptive reward functions are assumed to depend on predefined and fixed descriptive state representations. Alternatively, these two aspects may emerge interdependently: goals can shape the acquired state representations and vice versa. Here, we present a computational framework for state representation learning in bounded agents, where descriptive and prescriptive aspects are coupled through the notion of goal-directed, or telic, states. We introduce the concept of telic-controllability to characterize the tradeoff between the granularity of a telic state representation and the policy complexity required to reach all telic states. We propose an algorithm for learning telic-controllable state representations, illustrating it using a simulated navigation task. Our framework highlights the role of deliberate ignorance -- knowing what to ignore -- for learning state representations that balance goal flexibility and cognitive complexity.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

状态表示学习 目标导向 telic-controllability 认知复杂性
相关文章