paper-with-me

홈 › Papers

Plausibility-Based Heuristics for Latent Space Classical Planning

2023-06-20 · Yuta Takata, Alex Fukunaga

Recent work on LatPlan has shown that it is possible to learn models for domain-independent classical planners from unlabeled image data. Although PDDL models acquired by LatPlan can be solved using standard PDDL planners, the resulting latent-space plan may be invalid with respect to the underlying, ground-truth domain (e.g., the latent-space plan may include hallucinatory/invalid states). We propose Plausibility-Based Heuristics, which are domain-independent plausibility metrics which can be computed for each state evaluated during search and uses as a heuristic function for best-first search. We show that PBH significantly increases the number of valid found plans on image-based tile puzzle and Towers of Hanoi domains.

📄 PDF Abstract BibTeX arXiv:2306.11434

Code (0)

등록된 구현이 없습니다.

Tasks

valid

Similar Papers 제목 키워드 기반

Hierarchical Task Network Planning with LLM-Generated Heuristics

2026-05-08 · Felipe Meneguzzi, Alexandre Buchweitz, Augusto B. Corrêa, Victor Scherer Putrich 외 arxiv

HTN planning is a variation of classical planning where, instead of searching for a linear sequence of actions, an algorithm decomposes higher-level tasks using a method library until only executable actions remain. On o…

Planning as Goal Recognition: Deriving Heuristics from Intention Models -- Extended Version

2026-03-16 · Giacomo Rosa, Jean Honorio, Nir Lipovetzky, Sebastian Sardina arxiv

Classical planning aims to find a sequence of actions, a plan, that maps a starting state into one of the goal states. If a trajectory appears to be leading to the goal, should we prioritise exploring it? Seminal work in…

Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators

2021-09-30 · Clement Gehring, Masataro Asai, Rohan Chitnis, Tom Silver 외

Recent advances in reinforcement learning (RL) have led to a growing interest in applying RL to classical planning domains or applying classical planning methods to some complex RL domains. However, the long-horizon goal…

reinforcement-learningReinforcement Learning (RL)

Representation Learning for Classical Planning from Partially Observed Traces

2019-07-19 · Zhanhao Xiao, Hai Wan, Hankui Hankz Zhuo, Jinxia Lin 외

Specifying a complete domain model is time-consuming, which has been a bottleneck of AI planning technique application in many real-world scenarios. Most classical domain-model learning approaches output a domain model i…

Graph Neural NetworkRepresentation Learning

Rollout Heuristics for Online Stochastic Contingent Planning

2023-10-03 · Oded Blumenthal, Guy Shani

Partially observable Markov decision processes (POMDP) are a useful model for decision-making under partial observability and stochastic actions. Partially Observable Monte-Carlo Planning is an online algorithm for decid…

Decision Making