paper-with-me

홈 › Papers

A Bayesian Approach to Online Planning

2024-06-04 · Nir Greshler, David Ben Eli, Carmel Rabinovitz, Gabi Guetta, Liran Gispan, Guy Zohar, Aviv Tamar

The combination of Monte Carlo tree search and neural networks has revolutionized online planning. As neural network approximations are often imperfect, we ask whether uncertainty estimates about the network outputs could be used to improve planning. We develop a Bayesian planning approach that facilitates such uncertainty quantification, inspired by classical ideas from the meta-reasoning literature. We propose a Thompson sampling based algorithm for searching the tree of possible actions, for which we prove the first (to our knowledge) finite time Bayesian regret bound, and propose an efficient implementation for a restricted family of posterior distributions. In addition we propose a variant of the Bayes-UCB method applied to trees. Empirically, we demonstrate that on the ProcGen Maze and Leaper environments, when the uncertainty estimates are accurate but the neural network output is inaccurate, our Bayesian approach searches the tree much more effectively. In addition, we investigate whether popular uncertainty estimation methods are accurate enough to yield significant gains in planning. Our code is available at: https://github.com/nirgreshler/bayesian-online-planning.

📄 PDF Abstract BibTeX arXiv:2406.02103

Code (1)

nirgreshler/bayesian-online-planning 공식 구현

Tasks

Thompson SamplingUncertainty Quantification

Similar Papers 제목 키워드 기반

Online Incident Response Planning under Model Misspecification through Bayesian Learning and Belief Quantization

2025-08-20 · Kim Hammar, Tao Li arxiv

Effective responses to cyberattacks require fast decisions, even when information about the attack is incomplete or inaccurate. However, most decision-support frameworks for incident response rely on a detailed system mo…

Online Bayesian Goal Inference for Boundedly-Rational Planning Agents

2020-06-13 · Tan Zhi-Xuan, Jordyn L. Mann, Tom Silver, Joshua B. Tenenbaum 외

People routinely infer the goals of others by observing their actions over time. Remarkably, we can do so even when those actions lead to failure, enabling us to assist others when we detect that they might not achieve t…

Bayesian Inference

Online Bayesian Goal Inference for Boundedly Rational Planning Agents

2020-12-01 · NeurIPS 2020 12 · Tan Zhi-Xuan, Jordyn Mann, Tom Silver, Josh Tenenbaum 외

People routinely infer the goals of others by observing their actions over time. Remarkably, we can do so even when those actions lead to failure, enabling us to assist others when we detect that they might not achieve t…

Bayesian Inference

Bayesian Optimized Monte Carlo Planning

2020-10-07 · John Mern, Anil Yildiz, Zachary Sunberg, Tapan Mukerji 외

Online solvers for partially observable Markov decision processes have difficulty scaling to problems with large action spaces. Monte Carlo tree search with progressive widening attempts to improve scaling by sampling fr…

Bayesian Optimization

Constrained Bayesian Experimental Design via Online Planning

2026-05-26 · Yujia Guo, Daolang Huang, Xinyu Zhang, Sammie Katt 외 arxiv

Bayesian experimental design (BED) is a principled framework for data-efficient design of sequential experiments. However, existing BED methods are unable to adapt to dynamic constraints inherent in real-world tasks due …