Reinforcement learning algorithms with function approximation: recent advances and applications

DOI10.1016/J.INS.2013.08.037zbMATH Open1328.68176OpenAlexW2113921460MaRDI QIDQ903601FDOQ903601

Authors: Xin Xu, Lei Zuo, Zhenhua Huang 

Publication date: 14 January 2016

Published in: Information Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ins.2013.08.037

Recommendations

• A tutorial on linear function approximators for dynamic programming and reinforcement learning
• scientific article; zbMATH DE number 1950579
• Basis function adaptation in temporal difference reinforcement learning
• Q-Learning with Linear Function Approximation
• Reinforcement learning: a tutorial survey and recent advances

zbMATH Keywords

approximate dynamic programmingreinforcement learningfunction approximationgeneralizationlearning control

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• 10.1162/153244303768966085
• Title not available (Why is that?)
• Title not available (Why is that?)
• \({\mathcal Q}\)-learning
• Title not available (Why is that?)
• Title not available (Why is that?)
• Reinforcement learning for long-run average cost.
• The convergence of \(TD(\lambda)\) for general \(\lambda\)
• Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems
• Approximate Dynamic Programming
• Natural actor-critic algorithms
• Least squares policy evaluation algorithms with linear function approximation
• OnActor-Critic Algorithms
• 10.1162/1532443041827907
• Linear least-squares algorithms for temporal difference learning
• Adaptive stock trading with dynamic asset allocation using reinforcement learning
• An analysis of temporal-difference learning with function approximation
• Kernel-based reinforcement learning
• On graph kernels: hardness results and efficient alternatives.
• Algorithms for reinforcement learning.
• Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming
• Adaptive optimal control for continuous-time linear systems based on policy iteration
• Asynchronous stochastic approximation and Q-learning
• Stochastic approximation with two time scales
• Title not available (Why is that?)
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Title not available (Why is that?)
• Policy search for motor primitives in robotics
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
• Recent advances in hierarchical reinforcement learning
• Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
• Title not available (Why is that?)
• Multi-player non-zero-sum games: online adaptive learning solution of coupled Hamilton-Jacobi equations
• Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control
• Technical update: Least-squares temporal difference learning
• An upper bound on the loss from approximate optimal-value functions
• Convergence results for single-step on-policy reinforcement-learning algorithms
• Title not available (Why is that?)
• Model selection in reinforcement learning
• Adaptive-critic-based neural networks for aircraft optimal control
• Instrumental variable methods for system identification
• Title not available (Why is that?)
• Punish/Reward: Learning with a Critic in Adaptive Threshold Systems
• Markov decision processes with their applications
• Elevator group control using multiple reinforcement learning agents
• Integrating guidance into relational reinforcement learning
• Graph kernels and Gaussian processes for relational reinforcement learning
• Robot learning with GA-based fuzzy reinforcement learning agents
• Hybrid least-squares algorithms for approximate policy evaluation
• Title not available (Why is that?)

Cited In (25)

• Controlling estimation error in reinforcement learning via reinforced operation
• Neural circuits for learning context-dependent associations of stimuli
• Non-parametric value function approximation in robotics
• Advances in Neural Networks – ISNN 2005
• An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method
• Optimal distributed synchronization control for continuous-time heterogeneous multi-agent differential graphical games
• Reinforcement learning endowed with safe veto policies to learn the control of linked-multicomponent robotic systems
• Restricted gradient-descent algorithm for value-function approximation in reinforcement learning
• Embedded adaptive fuzzy controller based on reinforcement learning for DC motor with flexible shaft
• A reinforcement learning approach to distribution-free capacity allocation for sea cargo revenue management
• Editorial: some recent advances in learning and adaptation for uncertain feedback control systems
• A systematic study on meta-heuristic approaches for solving the graph coloring problem
• An integrated data-driven Markov parameters sequence identification and adaptive dynamic programming method to design fault-tolerant optimal tracking control for completely unknown model systems
• A Q-learning approach for investment decisions
• Dual heuristic programming with just‐in‐time modeling for self‐learning fault‐tolerant control of mobile robots
• Two-phase iteration for value function approximation and hyperparameter optimization in Gaussian-kernel-based adaptive critic design
• A lexicographic approach to constrained MDP admission control
• An approximate dynamic programming approach to resource management in multi-cloud scenarios
• Error controlled actor-critic
• Basis function adaptation in temporal difference reinforcement learning
• A unified DC programming framework and efficient DCA based approaches for large scale batch reinforcement learning
• Improved SARSA and DQN algorithms for reinforcement learning
• Neural-network-based robust optimal control design for a class of uncertain nonlinear systems via adaptive dynamic programming
• Data-based robust optimal control of continuous-time affine nonlinear systems with matched uncertainties
• Optimal scheduling for data transmission between mobile devices and cloud

Uses Software

• Approxrl

This page was built for publication: Reinforcement learning algorithms with function approximation: recent advances and applications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q903601)