scientific article; zbMATH DE number 7370614

MaRDI QIDQ4999027

Alberto Maria Metelli, Daniele Calandriello, Matteo Pirotta, Marcello Restelli

Publication date: 9 July 2021

Full work available at URL: https://jmlr.csail.mit.edu/papers/v22/19-707.html

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.

zbMATH Keywords

Markov decision processreinforcement learningapproximate dynamic programmingapproximate policy iterationpolicy chatteringpolicy oscillation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (2)

Smoothing policies and safe policy gradients ⋮ Efficient reductions in cyclotomic rings -- application to Ring LWE based FHE schemes

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the convergence of Neumann series in Banach space
• On the existence of fixed points for approximate value iteration and temporal-difference learning
• The Simplex and Policy-Iteration Methods Are Strongly Polynomial for the Markov Decision Problem with a Fixed Discount Rate
• Approximate policy iteration: a survey and some new methods
• The Linear Programming Approach to Approximate Dynamic Programming
• 10.1162/1532443041827907
• Perturbation bounds for the stationary probabilities of a finite Markov chain
• Information Theory

This page was built for publication: