From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning

DOI10.1613/jair.5575zbMath1426.68254OpenAlexW2787066086MaRDI QIDQ4605202

Leslie Pack Kaelbling, George D. Konidaris, Tomás Lozano-Pérez

Publication date: 7 March 2018

Published in: Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1613/jair.5575

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Artificial intelligence for robotics (68T40)

Related Items (8)

A Comprehensive Framework for Learning Declarative Action Models ⋮ Reward-respecting subtasks for model-based reinforcement learning ⋮ Unnamed Item ⋮ Challenges of real-world reinforcement learning: definitions, benchmarks and analysis ⋮ Learning action models with minimal observability ⋮ Gradient-based mixed planning with symbolic and numeric action parameters ⋮ A Sufficient Statistic for Influence in Structured Multiagent Environments ⋮ DeepSym: Deep Symbol Generation and Rule Learning for Planning from Unsupervised Robot Interaction

This page was built for publication: From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning