Reinforcement learning algorithms with function approximation: recent advances and applications

DOI10.1016/j.ins.2013.08.037zbMath1328.68176OpenAlexW2113921460MaRDI QIDQ903601

Lei Zuo, Xin Xu, Zhen-Hua 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

zbMATH Keywords

reinforcement learninggeneralizationlearning controlfunction approximationapproximate dynamic programming

Mathematics Subject Classification ID

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

Related Items (18)

Embedded adaptive fuzzy controller based on reinforcement learning for DC motor with flexible shaft ⋮ A unified DC programming framework and efficient DCA based approaches for large scale batch reinforcement learning ⋮ 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 ⋮ Two-phase iteration for value function approximation and hyperparameter optimization in Gaussian-kernel-based adaptive critic design ⋮ A systematic study on meta-heuristic approaches for solving the graph coloring problem ⋮ Neural circuits for learning context-dependent associations of stimuli ⋮ Dual heuristic programming with just‐in‐time modeling for self‐learning fault‐tolerant control of mobile robots ⋮ A reinforcement learning approach to distribution-free capacity allocation for sea cargo revenue management ⋮ Error controlled actor-critic ⋮ A Q-Learning Approach for Investment Decisions ⋮ An approximate dynamic programming approach to resource management in multi-cloud scenarios ⋮ Neural-network-based robust optimal control design for a class of uncertain nonlinear systems via adaptive dynamic programming ⋮ Reinforcement learning endowed with safe veto policies to learn the control of linked-multicomponent robotic systems ⋮ Optimal distributed synchronization control for continuous-time heterogeneous multi-agent differential graphical games ⋮ Optimal scheduling for data transmission between mobile devices and cloud ⋮ A lexicographic approach to constrained MDP admission control ⋮ Data-based robust optimal control of continuous-time affine nonlinear systems with matched uncertainties ⋮ Some recent advances in learning and adaptation for uncertain feedback control systems

Uses Software

• Approxrl

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems
• Policy search for motor primitives in robotics
• Model selection in reinforcement learning
• Multi-player non-zero-sum games: online adaptive learning solution of coupled Hamilton-Jacobi equations
• Integrating guidance into relational reinforcement learning
• Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming
• Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control
• Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
• Adaptive optimal control for continuous-time linear systems based on policy iteration
• Natural actor-critic algorithms
• Instrumental variable methods for system identification
• Elevator group control using multiple reinforcement learning agents
• Asynchronous stochastic approximation and Q-learning
• An upper bound on the loss from approximate optimal-value functions
• Stochastic approximation with two time scales
• Robot learning with GA-based fuzzy reinforcement learning agents
• Reinforcement learning for long-run average cost.
• Convergence results for single-step on-policy reinforcement-learning algorithms
• Kernel-based reinforcement learning
• Technical update: Least-squares temporal difference learning
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• \({\mathcal Q}\)-learning
• The convergence of \(TD(\lambda)\) for general \(\lambda\)
• Least squares policy evaluation algorithms with linear function approximation
• Hybrid least-squares algorithms for approximate policy evaluation
• Graph kernels and Gaussian processes for relational reinforcement learning
• Markov decision processes with their applications
• Adaptive stock trading with dynamic asset allocation using reinforcement learning
• 10.1162/153244303768966085
• Algorithms for Reinforcement Learning
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
• An analysis of temporal-difference learning with function approximation
• OnActor-Critic Algorithms
• Punish/Reward: Learning with a Critic in Adaptive Threshold Systems
• 10.1162/1532443041827907
• Adaptive-critic-based neural networks for aircraft optimal control
• Learning Theory and Kernel Machines
• Approximate Dynamic Programming
• Recent advances in hierarchical reinforcement learning

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