Approximate stochastic annealing for online control of infinite horizon Markov decision processes

DOI10.1016/j.automatica.2012.06.010zbMath1257.93113OpenAlexW1988071557MaRDI QIDQ1937498

Hyeong Soo Chang, Jiaqiao Hu

Publication date: 1 March 2013

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2012.06.010

zbMATH Keywords

algorithmssimulationstochastic approximationMarkov decision process

Mathematics Subject Classification ID

Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Optimal stochastic control (93E20)

Related Items

Model-Based Annealing Random Search with Stochastic Averaging

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A survey of some simulation-based algorithms for Markov decision processes
• Stochastic approximation methods for constrained and unconstrained systems
• Asynchronous stochastic approximation and Q-learning
• Convergence results for single-step on-policy reinforcement-learning algorithms
• Conditions for the uniqueness of optimal policies of discounted Markov decision processes
• New algorithms of the Q-learning type
• Reinforcement Learning: A Tutorial Survey and Recent Advances
• On the almost sure convergence of a general stochastic approximation procedure
• Cooling Schedules for Optimal Annealing
• Introduction to Stochastic Search and Optimization
• OnActor-Critic Algorithms
• A Simultaneous Perturbation Stochastic Approximation-Based Actor–Critic Algorithm for Markov Decision Processes
• An Asymptotically Efficient Simulation-Based Algorithm for Finite Horizon Stochastic Dynamic Programming
• Recursive Learning Automata Approach to Markov Decision Processes
• An Adaptive Sampling Algorithm for Solving Markov Decision Processes
• Probability Inequalities for Sums of Bounded Random Variables
• A Stochastic Approximation Method