Policy gradient in Lipschitz Markov decision processes

DOI10.1007/S10994-015-5484-1MaRDI QIDQ747252zbMATH OpenOpenAlexFDO

Authors Matteo Pirotta, Marcello Restelli, Luca Bascetta

Publication date 23 October 2015

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-015-5484-1

zbMATH Keywords

Markov decision processLipschitz continuityreinforcement learningpolicy gradient algorithm

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Methods of reduced gradient type (90C52)

Recommendations

• An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions
• On linear and super-linear convergence of natural policy gradient algorithm
• Lipschitz continuous policy functions for strongly concave optimization problems
• Policy gradient in continuous time
• Lipschitz continuity of value functions in Markovian decision processes

Cites work

• scientific article; zbMATH DE number 3137306 (Why is no real title available?)
• scientific article; zbMATH DE number 1304480 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 1507941 (Why is no real title available?)
• scientific article; zbMATH DE number 1753152 (Why is no real title available?)
• A Stochastic Approximation Method
• Collective motions of a shell structure
• Line search algorithms with guaranteed sufficient decrease
• Lipschitz continuity of value functions in Markovian decision processes
• Minimization of functions having Lipschitz continuous first partial derivatives
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• Policy search for motor primitives in robotics
• Solving connection and linearization problems within the Askey scheme and its \(q\)-analogue via inversion formulas
• Stochastic optimal control. The discrete time case

Cited in

(15)

• On linear and super-linear convergence of natural policy gradient algorithm
• On high-order differentiability of the policy function
• Learning parametric policies and transition probability models of Markov decision processes from data
• A Small Gain Analysis of Single Timescale Actor Critic
• Expected policy gradients for reinforcement learning
• Importance sampling techniques for policy optimization
• scientific article; zbMATH DE number 6982305 (Why is no real title available?)
• 10.1162/1532443041827907
• Risk-averse optimization of reward-based coherent risk measures
• scientific article; zbMATH DE number 5957492 (Why is no real title available?)
• Nonconvex policy search using variational inequalities
• Global convergence of policy gradient methods to (almost) locally optimal policies
• Lipschitz continuous policy functions for strongly concave optimization problems
• Smoothing policies and safe policy gradients
• On the sample complexity of actor-critic method for reinforcement learning with function approximation

This page was built for publication: Policy gradient in Lipschitz Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q747252)