Landmark-Assisted Monte Carlo Planning

David H. Chan, Mark Roberts, Dana S. Nau
8/15/2025
cs.AI

No official code found. Best implementation: dhrchan/lamp-pddlgym (0 stars, last commit 2025-08-15).

Abstract

Landmarks$\unicode{x2013}$conditions that must be satisfied at some point in every solution plan$\unicode{x2013}$have contributed to major advancements in classical planning, but they have seldom been used in stochastic domains. We formalize probabilistic landmarks and adapt the UCT algorithm to leverage them as subgoals to decompose MDPs; core to the adaptation is balancing between greedy landmark achievement and final goal achievement. Our results in benchmark domains show that well-chosen landmarks can significantly improve the performance of UCT in online probabilistic planning, while the best balance of greedy versus long-term goal achievement is problem-dependent. The results suggest that landmarks can provide helpful guidance for anytime algorithms solving MDPs.

View on arXivView PDF

Code Implementations(1)

dhrchan/lamp-pddlgymCommunity66%

Landmark-Assisted Monte Carlo Planning

00C, SASAug 15, 20251 years ago

Similar Papers

Revisiting Landmarks: Learning from Previous Plans to Generalize over Problem Instances

80% match2025

From domain-landmark graph learning to problem-landmark graph generation

79% match2025

Relevance Score: A Landmark-Like Heuristic for Planning

79% match2024

Value Iteration with Guessing for Markov Chains and Markov Decision Processes

79% match2025

Evaluating Game Difficulty in Tetris Block Puzzle

78% match2026

Stochastic Approximation with Block Coordinate Optimal Stepsizes

77% match2025

Cite this paper

@article{chan2025landmarkassisted,
  title  = {Landmark-Assisted Monte Carlo Planning},
  author = {David H. Chan and Mark Roberts and Dana S. Nau},
  year   = {2025},
  eprint = {2508.11493},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.11493v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.11493.svg)](https://codeofpaper.com/paper/2508.11493)

Discussion