PRP Rebooted: Advancing the State of the Art in FOND Planning
Christian Muise, Sheila A. McIlraith, J. Christopher Beck
摘要
Fully Observable Non-Deterministic (FOND) planning is a variant of classical symbolic planning in which actions are nondeterministic, with an action's outcome known only upon execution. It is a popular planning paradigm with applications ranging from robot planning to dialogue-agent design and reactive synthesis. Over the last 20 years, a number of approaches to FOND planning have emerged. In this work, we establish a new state of the art, following in the footsteps of some of the most powerful FOND planners to date. Our planner, PR2, decisively outperforms the four leading FOND planners, at times by a large margin, in 17 of 18 domains that represent a comprehensive benchmark suite. Ablation studies demonstrate the impact of various techniques we introduce, with the largest improvement coming from our novel FOND-aware heuristic.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper3
- Satisficing and Optimal Generalised Planning via Goal RegressionDillon Z. Chen, Till Hofmann, Toryn Q. Klassen, Sheila A. McIlraithAAAI 2026 · 被引用 1 次
- Planning with Uncertain Action ModelsFrancesco Percassi, Alessandro Saetti, Enrico ScalaAAAI 2026
- Dominance Pruning and Heuristics in Optimal Adversarial Non-Deterministic PlanningRasmus G. Tollund, Álvaro TorralbaAAAI 2026
相关 Paper
- Implicit Coordination Using FOND PlanningThorsten Engesser, Tim MillerAAAI 2020 · 被引用 4 次
- Strategic Reasoning over Golog Programs in the Nondeterministic Situation CalculusGiuseppe De Giacomo, Yves Lespérance, Matteo MancanelliAAAI 2026
- Robust Neuro-Symbolic Goal and Plan RecognitionLeonardo Amado, Ramon Fraga Pereira, Felipe MeneguzziAAAI 2023 · 被引用 14 次
- Search and Explore: Symbiotic Policy Synthesis in POMDPsRoman Andriushchenko, Alexander Bork, Milan Ceska, Sebastian Junges 等CAV 2023 · 被引用 7 次
- Symbolic Network: Generalized Neural Policies for Relational MDPsSankalp Garg, Aniket Bajpai, MausamICML 2020 · 被引用 39 次
