用条件生成模型提升高维状态下的信念表示与规划效率
Conditional Deep Generative Models for Belief State Planning
- 用条件生成模型替代传统信念表示，支持高维状态和大量观测
- 在矿产勘探任务中，信念准确率和规划性能均优于粒子滤波
- 适合机器人、自动驾驶等高维不确定环境中的决策问题
部分可观测马尔可夫决策过程（POMDP）被广泛用于机器人、自动驾驶和地下勘探等场景。然而，在高维状态空间下准确表示信念仍具挑战。本文提出一种基于条件深度生成模型（cDGM）的新方法，可高效处理高维状态与大规模观测数据，并从后验信念中生成任意数量样本。模型通过随机轨迹数据训练，在具有连续大状态空间的矿产勘探POMDP任务中表现优异。实验表明，cDGM在无任务依赖的信念准确度指标上优于粒子滤波基线，且在规划性能上也有显著提升。
原文摘要 · Abstract (English)
Partially observable Markov decision processes (POMDPs) are used to model a wide range of applications, including robotics, autonomous vehicles, and subsurface problems. However, accurately representing the belief is difficult for POMDPs with high-dimensional states. In this paper, we propose a novel approach that uses conditional deep generative models (cDGMs) to represent the belief. Unlike traditional belief representations, cDGMs are well-suited for high-dimensional states and large numbers of observations, and they can generate an arbitrary number of samples from the posterior belief. We train the cDGMs on data produced by random rollout trajectories and show their effectiveness in solving a mineral exploration POMDP with a large and continuous state space. The cDGMs outperform particle filter baselines in both task-agnostic measures of belief accuracy as well as in planning performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。