arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.07397cs.LGcs.AI
收藏

基于别名观测的潜在图快速探索与学习

Fast exploration and learning of latent graphs with aliased observations

Google DeepMind(谷歌DeepMind)

Miguel Lazaro-Gredilla, Ishan Deshpande, Sivaramakrishnan Swaminathan, Meet Dave, Dileep George

AI总结:

针对节点观测别名化且随机转移的潜在图恢复问题,提出一种高效探索算法,可在多种挑战性拓扑中指数级快于朴素探索,并在无别名情形下保持与基线相当的性能。

摘要:

我们研究恢复潜在图的问题,其中每个节点的观测是“别名化的”,且转移具有随机性。观测由一个在图中穿行的智能体收集。别名化意味着多个节点发出相同的观测,因此智能体无法知道自己位于哪个节点。智能体需要以尽可能少的步数、尽可能准确地揭示隐藏拓扑。这等价于在观测概率已知的部分可观测马尔可夫决策过程(POMDP)中高效恢复转移概率。本文提出了一种用于高效探索(并最终恢复)潜在图的算法。在多种具有别名观测的挑战性拓扑中,我们的方法比朴素探索快指数级;同时在无别名情形下,仍与现有基线保持竞争力。

英文摘要:

We consider the problem of recovering a latent graph where the observations at each node are \emph{aliased}, and transitions are stochastic. Observations are gathered by an agent traversing the graph. Aliasing means that multiple nodes emit the same observation, so the agent can not know in which node it is located. The agent needs to uncover the hidden topology as accurately as possible and in as few steps as possible. This is equivalent to efficient recovery of the transition probabilities of a partially observable Markov decision process (POMDP) in which the observation probabilities are known. An algorithm for efficiently exploring (and ultimately recovering) the latent graph is provided. Our approach is exponentially faster than naive exploration in a variety of challenging topologies with aliased observations while remaining competitive with existing baselines in the unaliased regime.

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。

↑