Abstraction and approximate decision-theoretic planning.
From MaRDI portal
Publication:1399130
DOI10.1016/S0004-3702(96)00023-9zbMath1042.68669MaRDI QIDQ1399130
Richard Dearden, Craig Boutilier
Publication date: 30 July 2003
Published in: Artificial Intelligence (Search for Journal in Brave)
optimizationalgorithmsdecision theoryapproximation theoryPlanningMarkovprocessesdecision-theoretic planningheuristic methods
Related Items
Practical solution techniques for first-order MDPs, Efficient incremental planning and learning with multi-valued decision diagrams, Exact decomposition approaches for Markov decision processes: a survey, Heuristic anytime approaches to stochastic decision processes, Multiple perspective dynamic decision making, Influence of modeling structure in probabilistic sequential decision problems, Stochastic dynamic programming with factored representations, A Sufficient Statistic for Influence in Structured Multiagent Environments, Equivalence notions and model minimization in Markov decision processes
Cites Work
- The *-minimax search procedure for trees containing chance nodes
- Deliberation scheduling for problem solving in time-constrained environments
- Automatically generating abstractions for planning
- Planning in a hierarchy of abstraction spaces
- STRIPS: A new approach to the application of theorem proving to problem solving
- A survey of algorithmic methods for partially observed Markov decision processes
- Real-time heuristic search
- Iterative Aggregation-Disaggregation Procedures for Discounted Semi-Markov Reward Processes
- Adaptive aggregation methods for infinite horizon dynamic programming
- Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
- The Optimal Control of Partially Observable Markov Processes over a Finite Horizon
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
