Using Expectation-Maximization for Reinforcement Learning

DOI10.1162/NECO.1997.9.2.271MaRDI QIDQ3125233zbMATH OpenOpenAlexFDO

Authors Peter Dayan, Geoffrey Hinton

Publication date 18 March 1997

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco.1997.9.2.271

zbMATH Keywords

learning algorithmrelative payoff procedure

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Reinforcement learning, sequential Monte Carlo and the EM algorithm
• 10.1162/153244303765208377
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Theory and use of the EM algorithm
• Stochastic dynamics of reinforcement learning

Cites work

• A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains
• Pattern-recognizing stochastic learning automata

Cited in

(22)

• Reinforcement distribution in fuzzy Q-learning
• Reinforcement learning with internal expectation for the random neural network
• Reinforcement learning, sequential Monte Carlo and the EM algorithm
• Theoretical foundation for CMA-ES from information geometry perspective
• An information-theoretic analysis of return maximization in reinforcement learning
• The asymptotic equipartition property in reinforcement learning and its relation to return maximization
• Reward-weighted regression with sample reuse for direct policy search in reinforcement learning
• Probabilistic inference for determining options in reinforcement learning
• Active inference and agency: optimal control without cost functions
• Modular inverse reinforcement learning for visuomotor behavior
• Policy search for motor primitives in robotics
• Optimal control as a graphical model inference problem
• Analysis and improvement of policy gradient estimation
• Non-parametric policy search with limited information loss
• Deep Reinforcement Learning: A State-of-the-Art Walkthrough
• scientific article; zbMATH DE number 7415125 (Why is no real title available?)
• Model-based Reinforcement Learning: A Survey
• Exact decomposition approaches for Markov decision processes: a survey
• Reinforcement learning in convergently non-stationary environments: feudal hierarchies and learned representations
• Leveraging probabilistic optimal control for efficient trajectory optimization
• Heterarchical reinforcement-learning model for integration of multiple cortico-striatal loops: fMRI examination in stimulus-action-reward association learning
• Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation

This page was built for publication: Using Expectation-Maximization for Reinforcement Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3125233)