Simulation-based optimization of Markov decision processes: an empirical process theory approach
From MaRDI portal
Publication:608432
DOI10.1016/j.automatica.2010.05.021zbMath1204.93132OpenAlexW2071767680MaRDI QIDQ608432
Publication date: 25 November 2010
Published in: Automatica (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.automatica.2010.05.021
Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Optimal stochastic control (93E20)
Related Items
Some Limit Properties of Markov Chains Induced by Recursive Stochastic Algorithms ⋮ Relevant states and memory in Markov chain bootstrapping and simulation ⋮ Empirical Dynamic Programming
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Simulation-based algorithms for Markov decision processes.
- Decision theoretic generalizations of the PAC model for neural net and other learning applications
- Learning and generalisation. With applications to neural networks.
- Approximate gradient methods in policy-space optimization of Markov reward processes
- Concentration of measure and isoperimetric inequalities in product spaces
- Simulation‐based Uniform Value Function Estimates of Markov Decision Processes
- Necessary and Sufficient Conditions for the Uniform Convergence of Means to their Expectations
- Uniform Central Limit Theorems
- Scale-sensitive dimensions, uniform convergence, and learnability
- Rate of Convergence of Empirical Measures and Costs in Controlled Markov Chains and Transient Optimality
- Conservation Laws, Extended Polymatroids and Multiarmed Bandit Problems; A Polyhedral Approach to Indexable Systems
- Neural Network Learning
- Dynamic Programming Conditions for Partially Observable Stochastic Systems
- On the Empirical State-Action Frequencies in Markov Decision Processes Under General Policies
