.png){kind=icon}
返回
Optimizing agent behavior over long time scales by transporting value
.png){kind=icon}
OA
AI
DOI：10.1038/s41467-019-13073-w.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Humans prolifically engage in mental time travel. We dwell on past actions and experience satisfaction or regret. More than storytelling, these recollections change how we act in the future and endow us with a computationally important ability to link actions and consequences across spans of time, which helps address the problem of long-term credit assignment: the question of how to evaluate the utility of actions within a long-duration behavioral sequence. Existing approaches to credit assignment in AI cannot solve tasks with long delays between actions and consequences. Here, we introduce a paradigm where agents use recall of specific memories to credit past actions, allowing them to solve problems that are intractable for existing algorithms. This paradigm broadens the scope of problems that can be investigated in AI and offers a mechanistic account of behaviors that may inspire models in neuroscience, psychology, and behavioral economics.
Keyword:
REINFORCEMENT
FUTURE
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
15.7
论文数:
9.4W
被引数:
91.2W
机构
暂无机构信息
引用论文
AMDIS & EXCEL: A Powerful Combination for Evaluating THM-Py-GC/MS Results from European Lacquers
PREAI
分享收藏Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
PREAI
分享收藏Reinforcement Learning and Episodic Memory in Humans and Animals: An Integrative Framework人类和动物的强化学习和情景记忆: 一个综合框架OAAI
OAAI分享收藏
Episodic Future Thinking Reduces Reward Delay Discounting through an Enhancement of Prefrontal-Mediotemporal Interactions.png)
NEURON
NEURONIF15
PREAI
分享收藏
查看更多内容