Construction of approximation spaces for reinforcement learning

zbMATH Open1317.68143MaRDI QIDQ2933876FDOQ2933876

Authors: Wendelin Böhmer, Steffen Grünewälder, Yun Shen, Marek Musial, Klaus Obermayer 

Publication date: 8 December 2014

Full work available at URL: http://jmlr.csail.mit.edu/papers/v14/boehmer13a.html

Recommendations

• Unsupervised basis function adaptation for reinforcement learning
• Sparse approximations to value functions in reinforcement learning
• 10.1162/1532443041827907
• Kernel-based reinforcement learning
• Practical kernel-based reinforcement learning

zbMATH Keywords

learningleast-squares policy iterationdiffusion distanceslow feature analysisproto value functionsvisual robot navigation

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Learning and adaptive systems in artificial intelligence (68T05)

Cited In (8)

• Sparse approximations to value functions in reinforcement learning
• Attainability of boundary points under reinforcement learning
• Unsupervised basis function adaptation for reinforcement learning
• Non-parametric policy search with limited information loss
• AI 2005: Advances in Artificial Intelligence
• Title not available (Why is that?)
• Algorithm of stable state spaces in reinforcement learning
• Policy iteration reinforcement learning based on geodesic Gaussian basis defined on a state-action graph

This page was built for publication: Construction of approximation spaces for reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2933876)