Practical solution techniques for first-order MDPs

DOI10.1016/J.ARTINT.2008.11.003zbMATH Open1191.68641OpenAlexW2089730874MaRDI QIDQ835833FDOQ835833

Authors: Scott Sanner, Craig Boutilier 

Publication date: 31 August 2009

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

Full work available at URL: https://doi.org/10.1016/j.artint.2008.11.003

Recommendations

• First order decision diagrams for relational MDPS
• Approximate linear programming for first-order MDPs
• Probabilistic relational planning with first order decision diagrams
• Decision-theoretic planning with generalized first-order decision diagrams
• Flucap: a heuristic search planner for first-order MDPS

zbMATH Keywords

planningfirst-order logicMDPs

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Markov and semi-Markov decision processes (90C40)

Cites Work

• Title not available (Why is that?)
• GOLOG: A logic programming language for dynamic domains
• Flucap: a heuristic search planner for first-order MDPS
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Stochastic Games
• Title not available (Why is that?)
• Title not available (Why is that?)
• STRIPS: A new approach to the application of theorem proving to problem solving
• Title not available (Why is that?)
• The FF planning system: Fast plan generation through heuristic search
• The Linear Programming Approach to Approximate Dynamic Programming
• Title not available (Why is that?)
• The independent choice logic for modelling multiple agents under uncertainty
• Generalized polynomial approximations in Markovian decision processes
• Title not available (Why is that?)
• Reasoning about noisy sensors and effectors in the situation calculus
• Relational reinforcement learning
• Title not available (Why is that?)
• Bucket elimination: A unifying framework for reasoning
• Feature-based methods for large scale dynamic programming
• Using temporal logics to express search control knowledge for planning
• First order decision diagrams for relational MDPS
• Practical solution techniques for first-order MDPs
• Solving factored mdps with hybrid state and action variables
• Title not available (Why is that?)
• Title not available (Why is that?)
• Approximate policy iteration with a policy language bias: solving relational Markov decision processes
• Abstraction and approximate decision-theoretic planning.
• Integrating guidance into relational reinforcement learning
• Title not available (Why is that?)
• Learning to take actions
• Learning action strategies for planning domains
• Graph kernels and Gaussian processes for relational reinforcement learning
• Influence of modeling structure in probabilistic sequential decision problems
• Approximate linear programming for first-order MDPs
• The factored policy-gradient planner

Cited In (22)

• Structured machine learning: the next ten years
• Elaboration Tolerant Representation of Markov Decision Process via Decision-Theoretic Extension of Probabilistic Action Language +
• Lifted model checking for relational MDPs
• Generalized planning as heuristic search: a new planning search-space that leverages pointers over objects
• A Comprehensive Framework for Learning Declarative Action Models
• The factored policy-gradient planner
• Weighted model counting without parameter variables
• Decision-theoretic planning with generalized first-order decision diagrams
• Discovering hidden structure in factored MDPs
• Practical solution techniques for first-order MDPs
• Approximate linear programming for first-order MDPs
• Approximate policy iteration with a policy language bias: solving relational Markov decision processes
• Bridging the gap between reinforcement learning and knowledge representation: a logical off- and on-policy framework
• First order decision diagrams for relational MDPS
• Qualitative numeric planning: reductions and complexity
• Title not available (Why is that?)
• The complexity of reasoning with FODD and GFODD
• Hierarchical decompositions and termination analysis for generalized planning
• Intensional dynamic programming. A rosetta stone for structured dynamic programming
• Relational linear programming
• Flucap: a heuristic search planner for first-order MDPS
• Probabilistic relational planning with first order decision diagrams

Uses Software

• GOLOG
• VAMPIRE
• Graphplan
• FODD-Planner
• FluCaP
• NMRDPP

This page was built for publication: Practical solution techniques for first-order MDPs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q835833)