arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.03311cs.LGcs.AI
收藏

使用智能体种群学习序列任务的嵌入

Learning Embeddings for Sequential Tasks Using Population of Agents

Max Planck Institute for Software Systems(马克斯·普朗克软件系统研究所)

Mridul Mahajan, Georgios Tzannetos, Goran Radanovic, Adish Singla

AI总结:

本文提出信息论框架,利用多样化智能体种群度量任务相似性并学习固定维度任务嵌入,在性能预测和任务选择两个场景中验证其有效性。

摘要:

我们提出了一个信息论框架,用于学习强化学习中任务的固定维度嵌入。我们利用这样一种思想:如果观察一个智能体在某一任务上的表现能够减少我们对其在另一任务上表现的不确定性,那么这两个任务就是相似的。这一直觉由我们的信息论准则所捕捉,该准则使用多样化的智能体种群作为智能体空间的近似,以在序列决策环境中衡量任务之间的相似性。除定性评估外,我们还通过在两个应用场景中与强基线进行定量比较,实证证明了基于任务嵌入的技术的有效性:通过观察智能体在小型任务测验上的表现来预测其在新任务上的表现,以及从给定的选项集合中选择具有期望特征的任务。

英文摘要:

We present an information-theoretic framework to learn fixed-dimensional embeddings for tasks in reinforcement learning. We leverage the idea that two tasks are similar if observing an agent's performance on one task reduces our uncertainty about its performance on the other. This intuition is captured by our information-theoretic criterion which uses a diverse agent population as an approximation for the space of agents to measure similarity between tasks in sequential decision-making settings. In addition to qualitative assessment, we empirically demonstrate the effectiveness of our techniques based on task embeddings by quantitative comparisons against strong baselines on two application scenarios: predicting an agent's performance on a new task by observing its performance on a small quiz of tasks, and selecting tasks with desired characteristics from a given set of options.

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。

↑