scientific article; zbMATH DE number 5658801

zbMath1200.68199MaRDI QIDQ5850827

No author found.

Publication date: 15 January 2010

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.

zbMATH Keywords

Markov decision processesreinforcement learningapproximate dynamic programmingMDPfactored MDPspartially observable MDPspolicy-gradient algorithmssequential decision-making under uncertainty

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Dynamic programming (90C39) Collections of articles of miscellaneous specific interest (00B15) Proceedings, conferences, collections, etc. pertaining to computer science (68-06) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Markov and semi-Markov decision processes (90C40) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Related Items (3)

Strategy Complexity of Point Payoff, Mean Payoff and Total Payoff Objectives in Countable MDPs ⋮ A unified DC programming framework and efficient DCA based approaches for large scale batch reinforcement learning ⋮ Computation of weighted sums of rewards for concurrent MDPs

This page was built for publication: