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 2605.11484cs.AI
收藏

参与过程:重新思考动作与观察的时间接口

Engagement Process: Rethinking the Temporal Interface of Action and Observation

University of Science and Technology of China(中国科学技术大学)

Jialian Li, Yuchen Cao, Junhong Liu, Weiran Guo, Xutao Wang, Jiaming Song, Jiahao Zhang, Jie Chen

AI总结:

本文提出参与过程(EP)模型,通过显式时间接口处理动作与观察的不同时间尺度交互,支持多速率协调和子系统组合,揭示隐藏的时间行为并使策略适应显式时间成本。

摘要:

在数字和物理环境中完成任务日益涉及复杂的时序交互,其中动作和观察在不同的时间尺度上展开,而非与固定观察-动作步骤对齐。为了建模此类交互,我们提出参与过程(EP),一种继承POMDP决策理论结构的交互形式,使时间在动作-观察接口中显式化。EP将动作和观察表示为沿时间解耦的事件流,而非在固定决策步骤上配对更新。此接口捕捉单agent的时间问题,如决策延迟、延迟反馈和持续动作,同时支持更丰富的agent侧组织、多速率协调和子系统间的组合交互。在玩具、LLM-agent和学习实验中,EP揭示了由基于步骤的接口隐藏的时间行为,并使策略在显式时间成本下适应。

英文摘要:

Task completion in digital and physical environments increasingly involves complex temporal interaction, where actions and observations unfold over different time scales rather than align with fixed observation--action steps. To model such interactions, we propose \emph{Engagement Process} (EP), an interaction formalism that inherits the decision-theoretic structure of POMDPs while making time explicit in the action--observation interface. EP represents actions and observations as decoupled event streams along time, rather than updates paired at fixed decision steps. This interface captures single-agent timing issues such as deliberation latency, delayed feedback, and persistent actions, while supporting richer agent-side organization, multi-rate coordination, and compositional interaction among subsystems. Across toy, LLM-agent, and learning experiments, EP exposes temporal behaviors hidden by step-based interfaces and enables policies to adapt under explicit time costs.

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。

↑