← Back to papers
2005 JMLR JMLR 2005

A Generalization Error for Q-Learning

Abstract

Planning problems that involve learning a policy from a single training set of finite horizon trajectories arise in both social science and medical fields. We consider Q-learning with function approximation for this setting and derive an upper bound on the generalization error. This upper bound is in terms of quantities minimized by a Q-learning algorithm, the complexity of the approximation space and an approximation term due to the mismatch between Q-learning and the goal of learning a policy that maximizes the value function. [abs] [ pdf ][ bib ] © JMLR 2005. (edit, beta)

🌱 Topic Pioneer — Deep RL
🌉 Interdisciplinary Bridge — Machine Learning and Reinforcement Learning
📈 Trend Setter — Deep RL
🧭 Keyword Pioneer — learning bound
🐣 Hot Topic Early Bird — function approximation
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Susan A. Murphy

Topics

Machine Learning > Optimization & Theory > Learning Theory Reinforcement Learning > Methods > Deep RL

Keywords

function approximation generalization error learning bound finite horizon
Download PDF

Related papers

Diffusion Kernels on Statistical Manifolds 2005
Learning with Decision Lists of Data-Dependent Features 2005
Multiclass Classification with Multi-Prototype Support Vector Machines 2005
Loopy Belief Propagation: Convergence and Effects of Message Errors 2005
Efficient Computation of Gapped Substring Kernels on Large Alphabets 2005