Learning Representation and Control in Markov Decision Processes: New Frontiers
From MaRDI portal
Publication:3580907
DOI10.1561/2200000003zbMath1192.93010MaRDI QIDQ3580907
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
Markov decision processes; Drazin inverse; generic algorithm; generalized spectral inverse of Laplacian; machine learning framework; representation policy iteration; solution of sequential decision problems
93A13: Hierarchical systems
93E35: Stochastic learning and adaptive control
90C40: Markov and semi-Markov decision processes
Related Items
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, Markov Reward Models and Markov Decision Processes in Discrete and Continuous Time: Performance Evaluation and Optimization