Q -Learning with Linear Function Approximation

No abstract is available for this paper.

• Publication year

  2007

• Venue

  Annual Conference Computational Learning Theory

• Publication date

  2007-06-13

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1007/978-3-540-72927-3_23
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Nonapproximability Results for Partially Observable Markov Decision Processes

  2011cited by this paper
• Advances in Neural Information Processing Systems pp MIT Press Generalization in Reinforcement Learning Successful Examples Using Sparse Coarse Coding

  2010cited by this paper
• Neuro-Dynamic Programming

  2009cited by this paper
• Convergence of Q-learning with linear function approximation

  2007cited by this paper
• Automatic basis function construction for approximate dynamic programming and reinforcement learning

  2006cited by this paper
• Basis Function Adaptation in Temporal Difference Reinforcement Learning

  2005cited by this paper
• Feature-Based Methods for Large Scale Dynamic Programming

  2005cited by this paper
• Explicit Manifold Representations for Value-Function Approximation in Reinforcement Learning

  2004cited by this paper
• Kernel-Based Reinforcement Learning

  2004cited by this paper
• Technical Note: Q-Learning

  2004cited by this paper
• Interpolation-based Q-learning

  2004influential reference
• Improved Temporal Difference Methods with Linear Function Approximation

  2004cited by this paper
• A ( Revised ) Survey of Approximate Methods for Solving Partially Observable Markov Decision Processes

  2003cited by this paper
• Near-Optimal Reinforcement Learning in Polynomial Time

  2002cited by this paper
• Technical Update: Least-Squares Temporal Difference Learning

  2002cited by this paper
• Off-Policy Temporal Difference Learning with Function Approximation

  2001cited by this paper
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning

  2000cited by this paper
• A LEARNING ALGORITHM FOR DISCRETE-TIME STOCHASTIC CONTROL

  2000influential reference
• Solving POMDP by Onolicy Linear Approximate Learning Algorithm

  1999cited by this paper
• Least-Squares Temporal Difference Learning

  1999cited by this paper
• Proceedings of the 1999 Conference on Information Sciences and Systems

  1999cited by this paper
• An Analysis of Temporal-Difference Learning with Function Approximation

  1998cited by this paper
• Learning and value function approximation in complex decision processes

  1998cited by this paper
• Exact and approximate algorithms for partially observable markov decision processes

  1998cited by this paper
• Learning Policies for Partially Observable Environments: Scaling Up

  1997cited by this paper
• Stochastic approximation with two time scales

  1997cited by this paper
• Locally Weighted Learning for Control

  1997cited by this paper
• General results on the convergence of stochastic algorithms

  1996cited by this paper
• Stable Function Approximation in Dynamic Programming

  1995cited by this paper
• Approximating Optimal Policies for Partially Observable Stochastic Domains

  1995cited by this paper
• Learning to Act Using Real-Time Dynamic Programming

  1995cited by this paper
• Temporal Difference Learning and TD-Gammon

  1995cited by this paper
• Learning from delayed rewards

  1995cited by this paper
• Feature-based methods for large scale dynamic programming

  1995cited by this paper
• Residual Algorithms: Reinforcement Learning with Function Approximation

  1995cited by this paper
• Generalization in Reinforcement Learning: Safely Approximating the Value Function

  1994cited by this paper
• Reinforcement Learning with Soft State Aggregation

  1994cited by this paper
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms

  1994cited by this paper
• TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play

  1994cited by this paper
• On-line Q-learning using connectionist systems

  1994cited by this paper
• Optimal Policies for Partially Observable Markov Decision Processes

  1994cited by this paper
• Markov Chains and Stochastic Stability

  1993cited by this paper
• Q-learning

  1992cited by this paper
• Dyna, an integrated architecture for learning, planning, and reacting

  1990cited by this paper
• Convergent activation dynamics in continuous time networks

  1989cited by this paper
• Learning to predict by the methods of temporal differences

  1988cited by this paper
• The Complexity of Markov Decision Processes

  1987cited by this paper

• Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning

  2025cites this paper
• Coverage Analysis for Digital Cousin Selection — Improving Multi-Environment Q-Learning

  2025cites this paper
• Linear Dynamics meets Linear MDPs: Closed-Form Optimal Policies via Reinforcement Learning

  2025cites this paper
• Quantum algorithm for apprenticeship learning

  2025cites this paper
• Reinforcement learning algorithm for reusable resource allocation with unknown rental time distribution

  2025cites this paper
• Provably Efficient and Agile Randomized Q-Learning

  2025cites this paper
• Reinforcement Learning for Individual Optimal Policy from Heterogeneous Data

  2025cites this paper
• Leveraging Digital Cousins for Ensemble Q-Learning in Large-Scale Wireless Networks

  2024cites this paper
• The costs of overcrowding (and release): Strategic discharges for isolated facilities during epidemiological outbreaks

  2024cites this paper
• Multi-Timescale Ensemble $Q$-Learning for Markov Decision Process Policy Optimization

  2024cites this paper
• Convex-Concave Zero-sum Markov Stackelberg Games

  2024cites this paper
• Reinforcement Learning Algorithm for Reusable Resource Allocation with Time-varying Reward

  2024cites this paper
• Optimistic Model Rollouts for Pessimistic Offline Policy Optimization

  2024cites this paper
• Adaptive Autonomous Driving Style Considering Human Trust

  2024cites this paper
• QRLIT: Quantum Reinforcement Learning for Database Index Tuning

  2024cites this paper
• Reward Machines for Deep RL in Noisy and Uncertain Environments

  2024cites this paper
• Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff

  2024cites this paper
• Learn to Optimize the Constrained Shortest Path on Large Dynamic Graphs

  2024cites this paper
• A Functional Model Method for Nonconvex Nonsmooth Conditional Stochastic Optimization

  2024cites this paper
• Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization

  2023cites this paper
• Matrix Low-Rank Trust Region Policy Optimization

  2023cites this paper
• Risk-averse control of Markov systems with value function learning

  2023cites this paper
• Data-Driven Optimal Control via Linear Programming: Boundedness Guarantees

  2023cites this paper
• On the Convergence and Sample Complexity Analysis of Deep Q-Networks with ε-Greedy Exploration

  2023cites this paper
• Multi-Bellman operator for convergence of Q-learning with linear function approximation

  2023cites this paper
• Sequential Learning Algorithms for Contextual Model-Free Influence Maximization

  2023cites this paper
• A Tale of Two Efficient Value Iteration Algorithms for Solving Linear MDPs with Large Action Space

  2023cites this paper
• Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation

  2023cites this paper
• Multi-agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation

  2023cites this paper
• Matrix Low-Rank Approximation for Policy Gradient Methods

  2023cites this paper
• Anticipatory Classifier System With Episode-Based Experience Replay

  2023cites this paper
• Variance-aware robust reinforcement learning with linear function approximation under heavy-tailed rewards

  2023cites this paper
• Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning

  2023cites this paper
• Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning

  2022cites this paper
• Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines

  2022cites this paper
• Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design

  2022cites this paper
• Target Network and Truncation Overcome The Deadly triad in Q-Learning

  2022cites this paper
• Improved Regret for Differentially Private Exploration in Linear MDP

  2022cites this paper
• A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning

  2022cites this paper
• Recent advances in reinforcement learning in finance

  2021cites this paper
• Energy Management Strategy for Smart Meter Privacy and Cost Saving

  2021cites this paper
• LiteIndex: Memory-Efficient Schema-Agnostic Indexing for JSON documents in SQLite

  2021cites this paper
• Echo State Networks for Reinforcement Learning

  2021influential citation
• Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation

  2021cites this paper
• Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm

  2021cites this paper
• Quantum agents in the Gym: a variational quantum algorithm for deep Q-learning

  2021cites this paper
• An L2 Analysis of Reinforcement Learning in High Dimensions with Kernel and Neural Network Approximation

  2021cites this paper
• Low-rank State-action Value-function Approximation

  2021cites this paper
• Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing

  2021cites this paper
• Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model

  2021cites this paper
• Theory and Application of Bonus-based Exploration in Reinforcement Learning

  2021cites this paper
• Accelerated Policy Evaluation: Learning Adversarial Environments with Adaptive Importance Sampling

  2021cites this paper
• Using Echo State Networks to Approximate Value Functions for Control

  2021influential citation
• Examining average and discounted reward optimality criteria in reinforcement learning

  2021influential citation
• Finite-time theory for momentum Q-learning

  2021cites this paper
• Actor-critic is implicitly biased towards high entropy optimal policies

  2021influential citation
• SCORE: Spurious COrrelation REduction for Offline Reinforcement Learning

  2021cites this paper
• Maxmin Q-learning: Controlling the Estimation Bias of Q-learning

  2020cites this paper
• ConQUR: Mitigating Delusional Bias in Deep Q-learning

  2020cites this paper
• Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning?

  2020cites this paper
• Nonstationary Reinforcement Learning with Linear Function Approximation

  2020cites this paper
• Energy management in wireless communications : from convex optimization to machine learning

  2020cites this paper
• Logistic $Q$-Learning

  2020cites this paper
• A Machine Learning Approach to 5G Infrastructure Market Optimization

  2020cites this paper
• Momentum Q-learning with Finite-Sample Convergence Guarantee

  2020cites this paper
• Towards Adaptive Packet Scheduler with Deep-Q Reinforcement Learning

  2020cites this paper
• FlapAI Bird: Training an Agent to Play Flappy Bird Using Reinforcement Learning Techniques

  2020cites this paper
• Agnostic Q -learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity

  2020cites this paper
• Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity

  2020cites this paper
• Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle

  2019cites this paper
• Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning

  2019influential citation
• Reinforcement Learning for Real-Time Optimization in NB-IoT Networks

  2019cites this paper
• Provably Efficient Reinforcement Learning with Linear Function Approximation

  2019cites this paper
• Adaptive Learning Recommendation Strategy Based on Deep Q-learning

  2019cites this paper
• Optimism in Reinforcement Learning with Generalized Linear Function Approximation

  2019cites this paper
• CAQL: Continuous Action Q-Learning

  2019cites this paper
• A reinforcement learning approach to personalized learning recommendation systems

  2018cites this paper
• Q-learning with Nearest Neighbors

  2018cites this paper
• Kinematic Synthesis Using Reinforcement Learning

  2018cites this paper
• Online Learning and Simulation Based Algorithms for Stochastic Optimization

  2018cites this paper
• A Deep Q-Network for the Beer Game : Using Machine Learning to Solve Inventory Optimization Problems

  2018cites this paper
• Deep Reinforcement Learning for Real-Time Optimization in NB-IoT Networks

  2018cites this paper
• Non-delusional Q-learning and value-iteration

  2018cites this paper
• Kernelized Q-Learning for Large-Scale, Potentially Continuous, Markov Decision Processes

  2018cites this paper
• Training Drift Counteraction Optimal Control Policies Using Reinforcement Learning: An Adaptive Cruise Control Example

  2018cites this paper
• A learning model for personalized adaptive cruise control

  2017cites this paper
• Reinforcement Learning for Multi-Step Expert Advice

  2017cites this paper
• A Deep Q-Network for the Beer Game: A Deep Reinforcement Learning algorithm to Solve Inventory Optimization Problems.

  2017cites this paper
• A function approximation approach to Reinforcement Learning for solving unit commitment problem with Photo voltaic sources

  2016cites this paper
• Cooperation and communication in multiagent deep reinforcement learning

  2016cites this paper
• Efficient Foraging of Limited Resources in a Multi-Agent System

  2015cites this paper
• Machine Learning Aided Decision Making and Adaptive Stochastic Control in a Hierarchical Interactive Smart Grid

  2015cites this paper
• Machine-Learning Aided Optimal Customer Decisions for an Interactive Smart Grid

  2015cites this paper
• Multiscale Q-learning with linear function approximation

  2015cites this paper
• A centralized reinforcement learning approach for proactive scheduling in manufacturing

  2015cites this paper
• Centralized learning and planning : for cognitive robots operating in human domains

  2014influential citation
• Virtual Machine Placement via Q-Learning with Function Approximation

  2014cites this paper
• Q-learning Reward Propagation Method for Reducing the Transmission Power of Sensor Nodes in Wireless Sensor Networks

  2013cites this paper
• A novel Q-learning algorithm with function approximation for constrained Markov decision processes

  2012cites this paper
• Adaptive function approximation in reinforcement learning with an interpolating growing neural gas

  2012cites this paper