paper-with-me

홈 › Papers

What Planning Problems Can A Relational Neural Network Solve?

2023-12-06 · NeurIPS 2023 11 · Jiayuan Mao, Tomás Lozano-Pérez, Joshua B. Tenenbaum, Leslie Pack Kaelbling

Goal-conditioned policies are generally understood to be "feed-forward" circuits, in the form of neural networks that map from the current state and the goal specification to the next action to take. However, under what circumstances such a policy can be learned and how efficient the policy will be are not well understood. In this paper, we present a circuit complexity analysis for relational neural networks (such as graph neural networks and transformers) representing policies for planning problems, by drawing connections with serialized goal regression search (S-GRS). We show that there are three general classes of planning problems, in terms of the growth of circuit width and depth as a function of the number of objects and planning horizon, providing constructive proofs. We also illustrate the utility of this analysis for designing neural networks for policy learning.

📄 PDF Abstract BibTeX arXiv:2312.03682

Code (1)

concepts-ai/goal-regression-width 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Scaling up Heuristic Planning with Relational Decision Trees

2014-01-16 · Tomas De la Rosa, Sergio Jimenez, Raquel Fuentetaja, Daniel Borrajo

Current evaluation functions for heuristic planning are expensive to compute. In numerous planning problems these functions provide good guidance to the solution, so they are worth the expense. However, when evaluation f…

General Classification

Planning with Noisy Probabilistic Relational Rules

2014-01-16 · Tobias Lang, Marc Toussaint

Noisy probabilistic relational rules are a promising world model representation for several reasons. They are compact and generalize over world instantiations. They are usually interpretable and they can be learned effec…

Robot Manipulation

Learning to Search and Searching to Learn for Generalization in Planning

2026-05-25 · Michael Aichmüller, Yannik Hesse, Hector Geffner arxiv

Combinatorial generalization remains a central challenge in Deep Reinforcement Learning (DRL). Classical planning provides a simple yet challenging setting to study this problem through explicit relational descriptions, …

Zero-shot GeneralizationReinforcement LearningGraph Neural Network

What you get is what you see: Decomposing Epistemic Planning using Functional STRIPS

2019-03-28 · Guang Hu, Tim Miller, Nir Lipovetzky

Epistemic planning --- planning with knowledge and belief --- is essential in many multi-agent and human-agent interaction domains. Most state-of-the-art epistemic planners solve this problem by compiling to propositiona…

Solving Relational MDPs with Exogenous Events and Additive Rewards

2013-06-26 · S. Joshi, R. Khardon, P. Tadepalli, A. Raghavan 외

We formalize a simple but natural subclass of service domains for relational planning problems with object-centered, independent exogenous events and additive rewards capturing, for example, problems in inventory control…