scientific article; zbMATH DE number 5037121
From MaRDI portal
Publication:5477860
DOI10.1023/A:1018008221616zbMath1099.90586MaRDI QIDQ5477860
Benjamin van Roy, John N. Tsitsiklis
Publication date: 29 June 2006
Published in: Machine Learning (Search for Journal in Brave)
Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.
featuresdynamic programmingreinforcement learningcurse of dimensionalityfunction approximationneuro-dynamic programmingCompact representation
Related Items
Practical solution techniques for first-order MDPs, Restricted gradient-descent algorithm for value-function approximation in reinforcement learning, ONLINE CAPACITY PLANNING FOR REHABILITATION TREATMENTS: AN APPROXIMATE DYNAMIC PROGRAMMING APPROACH, Q-learning and policy iteration algorithms for stochastic shortest path problems, Dynamic programming and value-function approximation in sequential decision problems: error analysis and numerical results, Policy iteration based feedback control, Water reservoir control under economic, social and environmental constraints, Q-learning with censored data, Continuous state dynamic programming via nonexpansive approximation, Basis function adaptation in temporal difference reinforcement learning, Approximate dynamic programming with a fuzzy parameterization, Decomposition of large-scale stochastic optimal control problems, Stochastic approximation algorithms: overview and recent trends., Stochastic decomposition applied to large-scale hydro valleys management, Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path, A hybrid dynamic programming -- Tabu search approach for the long-term hydropower scheduling problem, Stochastic dynamic programming with factored representations
