A Comprehensive Framework for Learning Declarative Action Models

DOI10.1613/JAIR.1.13073OpenAlexW4284967226MaRDI QIDQ5094057FDOQ5094057

Authors: Diego Aineto, Sergio Jimenez, Eva Onaindia 

Publication date: 2 August 2022

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

Full work available at URL: https://doi.org/10.1613/jair.1.13073

Recommendations

• scientific article
• Learning to act: qualitative learning of deterministic action models
• Learning partially observable non-deterministic action models
• scientific article; zbMATH DE number 5547939
• scientific article; zbMATH DE number 2111991
• Learning action models with minimal observability
• Learning probabilistic action models from interpretation transitions

zbMATH Keywords

planningknowledge engineering

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Planning as heuristic search
• Learning control knowledge for forward search planning
• Title not available (Why is that?)
• Title not available (Why is that?)
• Reinforcement learning. An introduction
• Planning with Markov decision processes. An AI perspective
• A Concise Introduction to Models and Methods for Automated Planning
• Belief tracking for planning with sensing: width, complexity and approximations
• Relational reinforcement learning
• Blocks World revisited
• Logical and Relational Learning
• Width and serialization of classical planning problems
• Learning action models from plan examples using weighted MAX-SAT
• Title not available (Why is that?)
• Practical solution techniques for first-order MDPs
• Title not available (Why is that?)
• Approximate policy iteration with a policy language bias: solving relational Markov decision processes
• Title not available (Why is that?)
• First-order logical filtering
• Learning generalized policies from planning examples using concept languages
• Reinforcement learning with factored states and actions
• Explanation in artificial intelligence: insights from the social sciences
• ADL and the State-Transition Model of Action
• Title not available (Why is that?)
• Learning action strategies for planning domains
• Relational reinforcement learning for planning with exogenous effects
• Learning to act: qualitative learning of deterministic action models
• Computing programs for generalized planning using a classical planner
• From skills to symbols: learning symbolic representations for abstract high-level planning
• Learning action models with minimal observability
• Title not available (Why is that?)
• Exploration in relational domains for model-based reinforcement learning
• Scaling up Heuristic Planning with Relational Decision Trees
• Brothers in arms? on AI planning and cellular automata
• Computing hierarchical finite state controllers with classical planning
• The computational support of scientific discovery

Cited In (4)

• A domain-independent agent architecture for adaptive operation in evolving open worlds
• Title not available (Why is that?)
• Detect, understand, act: a neuro-symbolic hierarchical reinforcement learning framework
• Title not available (Why is that?)

Uses Software

• PDDL

This page was built for publication: A Comprehensive Framework for Learning Declarative Action Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5094057)