Imagen de Portada

Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Aichmüller, Michael, Ståhlberg, Simon, Funkquist, Martin, Geffner, Hector
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Learning to Ground Existentially Quantified Goals
por: Funkquist, Martin, et al.
Publicado: (2024)

Sketch Decompositions for Classical Planning via Deep Reinforcement Learning
por: Aichmüller, Michael, et al.
Publicado: (2024)

Learning More Expressive General Policies for Classical Planning Domains
por: Ståhlberg, Simon, et al.
Publicado: (2024)

Learning to Search and Searching to Learn for Generalization in Planning
por: Aichmüller, Michael, et al.
Publicado: (2026)

Learning General Policies with Policy Gradient Methods
por: Ståhlberg, Simon, et al.
Publicado: (2025)

Symmetries and Expressive Requirements for Learning General Policies
por: Drexler, Dominik, et al.
Publicado: (2024)

First-Order Representation Languages for Goal-Conditioned RL
por: Ståhlberg, Simon, et al.
Publicado: (2025)

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains
por: Hofmann, Till, et al.
Publicado: (2024)

Learning General Policies From Examples
por: Bonet, Blai, et al.
Publicado: (2025)

Differentiable Learning of Lifted Action Schemas for Classical Planning
por: Reiter, Jonas, et al.
Publicado: (2026)

On Policy Reuse: An Expressive Language for Representing and Executing General Policies that Call Other Policies
por: Bonet, Blai, et al.
Publicado: (2024)

Learning Lifted STRIPS Models from Action Traces Alone: A Simple, General, and Scalable Solution
por: Gösgens, Jonas, et al.
Publicado: (2024)

Learning Lifted Action Models From Traces of Incomplete Actions and States
por: Jansen, Niklas, et al.
Publicado: (2025)

Learning Lifted Action Models from Traces with Minimal Information About Actions and States
por: Gösgens, Jonas, et al.
Publicado: (2026)

Policy Mirror Descent with Lookahead
por: Protopapas, Kimon, et al.
Publicado: (2024)

POrTAL: Plan-Orchestrated Tree Assembly for Lookahead
por: Conway, Evan, et al.
Publicado: (2025)

Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
por: Liu, Youwei, et al.
Publicado: (2026)

Encoding Reusable Multi-Robot Planning Strategies as Abstract Hypergraphs
por: Elimelech, Khen, et al.
Publicado: (2024)

Learning with Foresight: Enhancing Neural Routing Policy via Multi-Node Lookahead Prediction
por: Jiang, Xia, et al.
Publicado: (2026)

Policy Gradient with Tree Search: Avoiding Local Optimas through Lookahead
por: Koren, Uri, et al.
Publicado: (2025)

Lookahead Counterfactual Fairness
por: Zuo, Zhiqun, et al.
Publicado: (2024)

Constrained Decoding with Speculative Lookaheads
por: Nakshatri, Nishanth, et al.
Publicado: (2024)

Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents
por: Sohrabi, Shirin, et al.
Publicado: (2026)

ProAct: Agentic Lookahead in Interactive Environments
por: Yu, Yangbin, et al.
Publicado: (2026)

Pseudo-Boolean Proof Logging for Optimal Classical Planning
por: Dold, Simon, et al.
Publicado: (2025)

LLM-Evolved Pattern Generators for Optimal Classical Planning
por: Phung, Windy, et al.
Publicado: (2026)

Lookahead Drifting Model
por: Zhang, Guoqiang, et al.
Publicado: (2026)

Understanding Sample Generation Strategies for Learning Heuristic Functions in Classical Planning
por: Bettker, R. V., et al.
Publicado: (2022)

Lookahead Pathology in Monte-Carlo Tree Search
por: Nguyen, Khoi P. N., et al.
Publicado: (2022)

Dynamic-Width Speculative Beam Decoding for Efficient LLM Inference
por: Qin, Zongyue, et al.
Publicado: (2024)

From Next Token Prediction to (STRIPS) World Models
por: Núñez-Molina, Carlos, et al.
Publicado: (2025)

LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
por: Ahn, Jinwoo, et al.
Publicado: (2026)

Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving
por: Zhang, Jin, et al.
Publicado: (2025)

OledFL: Unleashing the Potential of Decentralized Federated Learning via Opposite Lookahead Enhancement
por: Li, Qinglun, et al.
Publicado: (2024)

Learning Abstract World Model for Value-preserving Planning with Options
por: Rodriguez-Sanchez, Rafael, et al.
Publicado: (2024)

On the Diminishing Returns of Width for Continual Learning
por: Guha, Etash, et al.
Publicado: (2024)

On Sample-Efficient Generalized Planning via Learned Transition Models
por: Gupta, Nitin, et al.
Publicado: (2026)

Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy
por: Zhao, Yao, et al.
Publicado: (2023)

Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
por: Lee, Sanghyun, et al.
Publicado: (2025)

Dynamic Lookahead Distance via Reinforcement Learning-Based Pure Pursuit for Autonomous Racing
por: Elgouhary, Mohamed, et al.
Publicado: (2026)