Practical solution techniques for first-order MDPs

DOI10.1016/j.artint.2008.11.003zbMath1191.68641OpenAlexW2089730874MaRDI QIDQ835833

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

zbMATH Keywords

first-order logicplanningMDPs

Mathematics Subject Classification ID

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

Related Items

The factored policy-gradient planner, Practical solution techniques for first-order MDPs, A Comprehensive Framework for Learning Declarative Action Models, The complexity of reasoning with FODD and GFODD, Decision-theoretic planning with generalized first-order decision diagrams, Qualitative Numeric Planning: Reductions and Complexity, Bridging the Gap between Reinforcement Learning and Knowledge Representation: A Logical Off- and On-Policy Framework, Relational linear programming, Discovering hidden structure in factored MDPs, Elaboration Tolerant Representation of Markov Decision Process via Decision-Theoretic Extension of Probabilistic Action Language +, Structured machine learning: the next ten years, Lifted model checking for relational MDPs, Weighted model counting without parameter variables

Uses Software

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

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Integrating guidance into relational reinforcement learning
• The factored policy-gradient planner
• Practical solution techniques for first-order MDPs
• Generalized polynomial approximations in Markovian decision processes
• Learning to take actions
• The independent choice logic for modelling multiple agents under uncertainty
• Abstraction and approximate decision-theoretic planning.
• Reasoning about noisy sensors and effectors in the situation calculus
• Using temporal logics to express search control knowledge for planning
• Bucket elimination: A unifying framework for reasoning
• Learning action strategies for planning domains
• Graph kernels and Gaussian processes for relational reinforcement learning
• STRIPS: A new approach to the application of theorem proving to problem solving
• Influence of modeling structure in probabilistic sequential decision problems
• The Linear Programming Approach to Approximate Dynamic Programming
• GOLOG: A logic programming language for dynamic domains
• Stochastic Games
• Relational reinforcement learning