Planning with Markov Decision Processes: An AI Perspective

DOI10.2200/S00426ED1V01Y201206AIM017zbMath1270.68014OpenAlexW4210976136MaRDI QIDQ2841739

Mausam Kolobov, Andrey V. Kolobov

Publication date: 29 July 2013

Published in: Synthesis Lectures on Artificial Intelligence and Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.2200/s00426ed1v01y201206aim017

Mathematics Subject Classification ID

Research exposition (monographs, survey articles) pertaining to computer science (68-02) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Probability in computer science (algorithm analysis, random structures, phase transitions, etc.) (68Q87)

Related Items (14)

Analyzing generalized planning under nondeterminism ⋮ Markov Reward Models and Markov Decision Processes in Discrete and Continuous Time: Performance Evaluation and Optimization ⋮ An approximate dynamic programming approach to the admission control of elective patients ⋮ A Comprehensive Framework for Learning Declarative Action Models ⋮ The stochastic shortest path problem: a polyhedral combinatorics perspective ⋮ An anytime algorithm for constrained stochastic shortest path problems with deterministic policies ⋮ GUBS criterion: arbitrary trade-offs between cost and probability-to-goal in stochastic planning based on expected utility theory ⋮ Planning in hybrid relational MDPs ⋮ Plan aggregation for strong cyclic planning in nondeterministic domains ⋮ Robust topological policy iteration for infinite horizon bounded Markov decision processes ⋮ An Overview for Markov Decision Processes in Queues and Networks ⋮ Deliberative acting, planning and learning with hierarchical operational models ⋮ A Markov decision model with dead ends for operating room planning considering dynamic patient priority ⋮ Bottom-up learning of hierarchical models in a class of deterministic pomdp environments

This page was built for publication: Planning with Markov Decision Processes: An AI Perspective