Saved in:
Bibliographic Details
Main Authors: Yadav, Sandarbh, Maliakkal, Frederic J, Khadilkar, Harshad, Kalyanakrishnan, Shivaram
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.04732
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918486006038528
author Yadav, Sandarbh
Maliakkal, Frederic J
Khadilkar, Harshad
Kalyanakrishnan, Shivaram
author_facet Yadav, Sandarbh
Maliakkal, Frederic J
Khadilkar, Harshad
Kalyanakrishnan, Shivaram
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04732
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Using Common Random Numbers for Simulation-based Planning with Rollouts
Yadav, Sandarbh
Maliakkal, Frederic J
Khadilkar, Harshad
Kalyanakrishnan, Shivaram
Machine Learning
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.
title Using Common Random Numbers for Simulation-based Planning with Rollouts
topic Machine Learning
url https://arxiv.org/abs/2605.04732