Abstract:Simulation-based planning with rollouts is a widely-deployed technique for decision making in stochastic environments. The primary instrument of simulation-based planning is a sampling model, which is repeatedly called to generate trajectories and estimate the utilities of available actions. Among the actions thus explored, one with the maximum estimated utility is then executed. In this paper, we examine the effect of using common random numbers in the simulation process. We obtain a simple recipe for (provably) reducing variance in relative utility when simulations invoke a rollout policy beyond some depth. Experiments on synthetic tasks confirm that our scheme improves task performance. The broader significance of our innovation is apparent from two practical applications: (1) single-step lookahead planning in a pension-disbursement task, and (2) a deployment of the well-known UCT algorithm for the game of Ludo.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.04732 [cs.LG] |
| (or arXiv:2605.04732v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.04732 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Reinforcement Learning Journal 2026 |
From: Harshad Khadilkar [view email]
[v1]
Wed, 6 May 2026 10:31:18 UTC (1,430 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。