Adaptive aggregation methods for infinite horizon dynamic programming
From MaRDI portal
Publication:3830830
DOI10.1109/9.24227zbMath0675.90089OpenAlexW2101167844MaRDI QIDQ3830830
Dimitri P. Bertsekas, David A. Castanon
Publication date: 1989
Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1109/9.24227
successive approximationinfinite horizon dynamic programmingmultiple ergodic classesaggregation iterations
Related Items
Adaptive differential dynamic programming for multiobjective optimal control ⋮ Numerical methods for controlled and uncontrolled multiplexing and queueing systems ⋮ An incremental off-policy search in a model-free Markov decision process using a single sample path ⋮ Approximate dynamic programming with state aggregation applied to UAV perimeter patrol ⋮ Block-scaling of value-iteration for discounted Markov renewal programming ⋮ Replacement process decomposition for discounted Markov renewal programming ⋮ Generic rank-one corrections for value iteration in Markovian decision problems ⋮ Feature-based methods for large scale dynamic programming ⋮ Two adaptively stepped monotone algorithms for solving discounted dynamic programming equations ⋮ Adaptive aggregation for reinforcement learning in average reward Markov decision processes ⋮ A variable neighborhood search based algorithm for finite-horizon Markov decision processes ⋮ Abstraction and approximate decision-theoretic planning. ⋮ Agent's actions as a classification criteria for the state space in a learning from rewards system ⋮ Multilevel Preconditioners for Temporal-Difference Learning Methods Related to Recommendation Engines ⋮ Auction algorithms for network flow problems: A tutorial introduction ⋮ What you should know about approximate dynamic programming ⋮ Near optimization of dynamic systems by decomposition and aggregation ⋮ Stochastic dynamic programming with factored representations ⋮ Bounded-parameter Markov decision processes ⋮ An aggregation-based approximate dynamic programming approach for the periodic review model with random yield ⋮ Approximate dynamic programming via iterated Bellman inequalities ⋮ Estimating equilibrium probabilities for band diagonal Markov chains using aggregation and disaggregation techniques ⋮ Solving factored MDPs using non-homogeneous partitions
