Regularized policy iteration with nonparametric function spaces

zbMATH Open1392.68345MaRDI QIDQ2834459FDOQ2834459

Authors: Amir-Massoud Farahmand, Mohammad Ghavamzadeh, Csaba Szepesvári, Shie Mannor 

Publication date: 22 November 2016

Published in: Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL: http://jmlr.csail.mit.edu/papers/v17/13-016.html

Recommendations

• Nonconvex policy search using variational inequalities
• Policy iterations for reinforcement learning problems in continuous time and space -- fundamental theory and methods
• Non-parametric policy search with limited information loss
• Approximate gradient methods in policy-space optimization of Markov reward processes
• Reinforcement learning with approximation spaces
• Smoothed functional-based gradient algorithms for off-policy reinforcement learning: a non-asymptotic viewpoint
• Stochastic Policy Gradient Ascent in Reproducing Kernel Hilbert Spaces
• Approximate policy optimization and adaptive control in regression models
• Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
• On the theory of policy gradient methods: optimality, approximation, and distribution shift

zbMATH Keywords

regularizationreinforcement learningapproximate policy iterationfinite-sample analysisnon-parametric method

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Markov and semi-Markov decision processes (90C40)

Cited In (20)

• A multiagent reinforcement learning framework for off-policy evaluation in two-sided markets
• Off-policy estimation of long-term average outcomes with applications to mobile health
• Batch policy learning in average reward Markov decision processes
• Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning
• Model selection in reinforcement learning
• Performance guarantees for policy learning
• Low-Rank Representation of Reinforcement Learning Policies
• Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path
• On high-order differentiability of the policy function
• Nonparametric approximation generalized policy iteration reinforcement learning algorithm based on states clustering
• Projected state-action balancing weights for offline reinforcement learning
• Value Enhancement of Reinforcement Learning via Efficient and Robust Trust Region Optimization
• Optimal policy evaluation using kernel-based temporal difference methods
• Analysis of classification-based policy iteration algorithms
• Learning when-to-treat policies
• Policy mirror descent for reinforcement learning: linear convergence, new sampling complexity, and generalized problem classes
• Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path
• Multi-agent reinforcement learning: a selective overview of theories and algorithms
• A review of stochastic algorithms with continuous value function approximation and some new approximate policy iteration algorithms for multidimensional continuous applications
• A mathematical perspective of machine learning

This page was built for publication: Regularized policy iteration with nonparametric function spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2834459)