Reinforcement Learning: Stochastic Approximation Algorithms for Markov Decision Processes

2015/12/23 by Vikram Krishnamurthy, Krishnamurthy, Vikram
Computer Science · Decision Sciences · #Advanced Multi-Objective Optimization Algorithms #FOS: Mathematics #Optimization and Control (math.OC) #Reinforcement Learning in Robotics #Simulation Techniques and Applications

paper · pdf · doi:10.48550/arxiv.1512.07669

openalex publication_date 2015/12/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This article presents a short and concise description of stochastic approximation algorithms in reinforcement learning of Markov decision processes. The algorithms can also be used as a suboptimal method for partially observed Markov decision processes.

Related

• A Tutorial Introduction to Reinforcement Learning
• Reinforcement Learning with Unbiased Policy Evaluation and Linear Function Approximation
• Stability of Stochastic Approximations with `Controlled Markov' Noise and Temporal Difference Learning
• Stochastic Approximation with Markov Noise: Analysis and applications in reinforcement learning
• Reinforcement Learning When All Actions are Not Always Available