Learning Representation and Control in Markov Decision Processes: New Frontiers

DOI10.1561/2200000003zbMath1192.93010OpenAlexW2072054128MaRDI QIDQ3580907

Sridhar Mahadevan

Publication date: 14 August 2010

Published in: Foundations and Trends® in Machine Learning (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/481dc549e4fc8e0895fe98080dcd6fba138f7136

zbMATH Keywords

Markov decision processesDrazin inversegeneric algorithmgeneralized spectral inverse of Laplacianmachine learning frameworkrepresentation policy iterationsolution of sequential decision problems

Mathematics Subject Classification ID

Hierarchical systems (93A13) Stochastic learning and adaptive control (93E35) Markov and semi-Markov decision processes (90C40)

Related Items (5)

Markov Reward Models and Markov Decision Processes in Discrete and Continuous Time: Performance Evaluation and Optimization ⋮ Framing reinforcement learning from human reward: reward positivity, temporal discounting, episodicity, and performance ⋮ Dimension reduction and its application to model-based exploration in continuous spaces ⋮ A new decision making model based on rank centrality for GDM with fuzzy preference relations ⋮ Model-based Reinforcement Learning: A Survey

This page was built for publication: Learning Representation and Control in Markov Decision Processes: New Frontiers