Variance-penalized Markov decision processes: dynamic programming and reinforcement learning techniques

DOI10.1080/03081079.2014.883387zbMath1295.90101OpenAlexW2024928738MaRDI QIDQ5166474

Abhijit Gosavi

Publication date: 27 June 2014

Published in: International Journal of General Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/03081079.2014.883387

zbMATH Keywords

dynamic programmingBellman equationreinforcement learningrisk penaltiesvariance-penalized MDPs

Mathematics Subject Classification ID

Dynamic programming (90C39) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Markov and semi-Markov decision processes (90C40)

Related Items (6)

A unified algorithm framework for mean-variance optimization in discounted Markov decision processes ⋮ Approximate solutions to constrained risk-sensitive Markov decision processes ⋮ A Reinforcement Learning Neural Network for Robotic Manipulator Control ⋮ A performance-centred approach to optimising maintenance of complex systems ⋮ Reinforcement learning ⋮ Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Simulation-based algorithms for Markov decision processes.
• Optimal threshold probability and expectation in semi-Markov decision processes
• Minimizing risk models in Markov decision processes with policies depending on target values
• Convergence results for single-step on-policy reinforcement-learning algorithms
• Risk-sensitive reinforcement learning
• Target-level criterion in Markov decision processes
• Minimum risk probability for finite horizon semi-Markov decision processes
• Minimising a threshold probability in discounted Markov decision processes
• Risk-sensitive capacity control in revenue management
• Time consistent dynamic risk measures
• A risk-sensitive approach to total productive maintenance
• Learning Algorithms for Markov Decision Processes with Average Cost
• Variance-Penalized Markov Decision Processes
• Risk-sensitive control with HARA utility
• The variance of discounted Markov decision processes
• Percentile performance criteria for limiting average Markov decision processes
• Constrained Optimization for Average Cost Continuous-Time Markov Decision Processes
• Risk-Sensitive Markov Decision Processes

This page was built for publication: Variance-penalized Markov decision processes: dynamic programming and reinforcement learning techniques