Algorithms for reinforcement learning.

DOI10.2200/S00268ED1V01Y201005AIM009zbMATH Open1205.68320OpenAlexW4211221179MaRDI QIDQ3588852FDOQ3588852

Authors: Csaba Szepesvári 

Publication date: 10 September 2010

Published in: Synthesis Lectures on Artificial Intelligence and Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.2200/s00268ed1v01y201005aim009

Recommendations

• Reinforcement learning. An introduction
• Reinforcement learning theory, algorithms and its application
• scientific article; zbMATH DE number 1950579
• Reinforcement learning: a tutorial survey and recent advances
• Statistical reinforcement learning. Modern machine learning approaches

zbMATH Keywords

planningsimulationstochastic approximationleast-squares methodsMarkov decision processesonline learningreinforcement learningfunction approximationQ-learningPAC-learningactive learningnatural gradientbias-variance tradeoffoverfittingstochastic gradient methodspolicy gradienttemporal difference learningactor-critic methods

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Research exposition (monographs, survey articles) pertaining to computer science (68-02) Dynamic programming (90C39) Nonnumerical algorithms (68W05) Markov and semi-Markov decision processes (90C40)

Cited In (55)

• Undiscounted reinforcement learning algorithm based on performance potentials
• A Two-Timescale Stochastic Algorithm Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic
• Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model
• Efficient augmentation and relaxation learning for individualized treatment rules using observational data
• Investigating the properties of neural network representations in reinforcement learning
• On learning and branching: a survey
• Closed-form Approximations in Multi-asset Market Making
• Preference-based reinforcement learning: evolutionary direct policy search using a preference-based racing algorithm
• Model selection in reinforcement learning
• Adaptive representations for reinforcement learning.
• Statistical reinforcement learning. Modern machine learning approaches
• Dynamic treatment regimes: technical challenges and applications
• Convergence of entropy-regularized natural policy gradient with linear function approximation
• Bayesian exploration for approximate dynamic programming
• Markov decision processes with sequential sensor measurements
• Adaptive playouts for online learning of policies during Monte Carlo tree search
• Continuous-action planning for discounted infinite-horizon nonlinear optimal control with Lipschitz values
• Editorial: some recent advances in learning and adaptation for uncertain feedback control systems
• Optimal activation of halting multi‐armed bandit models
• Asymptotic analysis of value prediction by well-specified and misspecified models
• A Reinforcement Learning Neural Network for Robotic Manipulator Control
• Non-parametric policy search with limited information loss
• Structure in machine learning
• Robust adaptive dynamic programming for linear and nonlinear systems: an overview
• A systematic study on meta-heuristic approaches for solving the graph coloring problem
• Abstraction from demonstration for efficient reinforcement learning in high-dimensional domains
• On convergence of value iteration for a class of total cost Markov decision processes
• Title not available (Why is that?)
• A convex optimization approach to dynamic programming in continuous state and action spaces
• TEXPLORE: temporal difference reinforcement learning for robots and time-constrained domains
• Least squares policy iteration with instrumental variables vs. direct policy search: comparison against optimal benchmarks using energy storage
• Empirical \(Q\)-value iteration
• Reinforcement learning. An introduction
• Efficient model-based reinforcement learning for approximate online optimal control
• Approximate Q Learning for Controlled Diffusion Processes and Its Near Optimality
• A unified DC programming framework and efficient DCA based approaches for large scale batch reinforcement learning
• Reinforcement learning agents
• Title not available (Why is that?)
• Deep reinforcement trading with predictable returns
• Title not available (Why is that?)
• Formalization of methods for the development of autonomous artificial intelligence systems
• Crowd computing as a cooperation problem: An evolutionary approach
• Title not available (Why is that?)
• Online spatio-temporal matching in stochastic and dynamic domains
• Hypervolume indicator and dominance reward based multi-objective Monte-Carlo tree search
• Modern Bayesian experimental design
• Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning
• Deep exploration via randomized value functions
• Finite-time performance of distributed temporal-difference learning with linear function approximation
• Reinforcement learning theory, algorithms and its application
• Reinforcement learning algorithms with function approximation: recent advances and applications
• Fundamental design principles for reinforcement learning algorithms
• Proximal algorithms and temporal difference methods for solving fixed point problems
• Decision making under uncertainty and reinforcement learning. Theory and algorithms
• A unified framework for stochastic optimization

Uses Software

• R-MAX

This page was built for publication: Algorithms for reinforcement learning.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3588852)