Policy gradient in Lipschitz Markov decision processes

DOI10.1007/S10994-015-5484-1zbMATH Open1354.90166OpenAlexW2046859786MaRDI QIDQ747252FDOQ747252

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

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

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)

Cites Work

• Title not available (Why is that?)
• A Stochastic Approximation Method
• Line search algorithms with guaranteed sufficient decrease
• Stochastic optimal control. The discrete time case
• Minimization of functions having Lipschitz continuous first partial derivatives
• Solving connection and linearization problems within the Askey scheme and its \(q\)-analogue via inversion formulas
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• Policy search for motor primitives in robotics
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Lipschitz continuity of value functions in Markovian decision processes
• Collective motions of a shell structure
• Title not available (Why is that?)

Cited In (15)

• Title not available (Why is that?)
• 10.1162/1532443041827907
• A Small Gain Analysis of Single Timescale Actor Critic
• On the sample complexity of actor-critic method for reinforcement learning with function approximation
• Nonconvex policy search using variational inequalities
• On high-order differentiability of the policy function
• Expected policy gradients for reinforcement learning
• Importance sampling techniques for policy optimization
• Title not available (Why is that?)
• Lipschitz continuous policy functions for strongly concave optimization problems
• On linear and super-linear convergence of natural policy gradient algorithm
• Risk-averse optimization of reward-based coherent risk measures
• Smoothing policies and safe policy gradients
• Global convergence of policy gradient methods to (almost) locally optimal policies
• Learning parametric policies and transition probability models of Markov decision processes from data

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)