# Diverse, Top-k, and Top-Quality Planning Over Simulators

arXiv: https://arxiv.org/abs/2308.13147 · HTML: https://mlsanity.com/paper/2308.13147/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 33 references that are in the map.
- First posted on arXiv 25 Aug 2023.

## Builds on (most cited first, 4 of 4)

- [Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning](https://mlsanity.com/paper/2004.11410/) (2020)
- [Modelling Strategic Deceptive Planning in Adversarial Multi-Agent Systems](https://mlsanity.com/paper/2109.03092/) (2021)
- [Multi-Agent Simulation for AI Behaviour Discovery in Operations Research](https://mlsanity.com/paper/2108.13296/) (2021)
- [Strategy Extraction in Single-Agent Games](https://mlsanity.com/paper/2305.12623/) (2023)

## Built on by (most cited first, 3 of 3)

- [Diverse Planning with Simulators via Linear Temporal Logic](https://mlsanity.com/paper/2510.17418/) (2025)
- [Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork](https://mlsanity.com/paper/2607.27177/) (2026)
- [Local Optima in Diversity Optimization: Non-trivial Offspring Population is Essential](https://mlsanity.com/paper/2407.08963/) (2024)

## Abstract (arXiv)

Diverse, top-k, and top-quality planning are concerned with the generation of sets of solutions to sequential decision problems. Previously this area has been the domain of classical planners that require a symbolic model of the problem instance. This paper proposes a novel alternative approach that uses Monte Carlo Tree Search (MCTS), enabling application to problems for which only a black-box simulation model is available. We present a procedure for extracting bounded sets of plans from pre-generated search trees in best-first order, and a metric for evaluating the relative quality of paths through a search tree. We demonstrate this approach on a path-planning problem with hidden information, and suggest adaptations to the MCTS algorithm to increase the diversity of generated plans. Our results show that our method can generate diverse and high-quality plan sets in domains where classical planners are not applicable.