Learning Algorithms for Markov Decision Processes with Average Cost

DOI10.1137/S0363012999361974zbMath1001.93091OpenAlexW2154204727MaRDI QIDQ2753225

Dimitri P. Bertsekas, Vivek S. Borkar, Jinane Abounadi

Publication date: 29 October 2001

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/s0363012999361974

zbMATH Keywords

stabilityrelative value iteration algorithm

Mathematics Subject Classification ID

Dynamic programming in optimal control and differential games (49L20) Optimal stochastic control (93E20) Stochastic approximation (62L20) Stochastic stability in control theory (93E15) Markov and semi-Markov decision processes (90C40)

Related Items (26)

Multiscale Q-learning with linear function approximation ⋮ A sojourn-based approach to semi-Markov reinforcement learning ⋮ Deep reinforcement learning for wireless sensor scheduling in cyber-physical systems ⋮ Risk-Sensitive Reinforcement Learning via Policy Gradient Search ⋮ A framework for transforming specifications in reinforcement learning ⋮ Optimal sensor scheduling for remote state estimation with limited bandwidth: a deep reinforcement learning approach ⋮ Stochastic Fixed-Point Iterations for Nonexpansive Maps: Convergence and Error Bounds ⋮ Approachability in Stackelberg stochastic games with vector costs ⋮ Analyzing anonymity attacks through noisy channels ⋮ Solutions of the average cost optimality equation for Markov decision processes with weakly continuous kernel: the fixed-point approach revisited ⋮ Q-learning for Markov decision processes with a satisfiability criterion ⋮ Variance-penalized Markov decision processes: dynamic programming and reinforcement learning techniques ⋮ Learning dynamic prices in electronic retail markets with customer segmentation ⋮ Optimal Distributed Uplink Channel Allocation: A Constrained MDP Formulation ⋮ Opportunistic Transmission over Randomly Varying Channels ⋮ Empirical Dynamic Programming ⋮ Fitted Q-iteration by functional networks for control problems ⋮ A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs ⋮ Look-ahead control of conveyor-serviced production station by using potential-based online policy iteration ⋮ Natural actor-critic algorithms ⋮ Dynamic pricing models for electronic business ⋮ Fundamental design principles for reinforcement learning algorithms ⋮ Empirical Q-Value Iteration ⋮ Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities ⋮ Batch policy learning in average reward Markov decision processes ⋮ Whittle index based Q-learning for restless bandits with average reward

This page was built for publication: Learning Algorithms for Markov Decision Processes with Average Cost