Efficient exploration through active learning for value function approximation in reinforcement learning

DOI10.1016/j.neunet.2009.12.010zbMath1396.68086OpenAlexW2160095661WikidataQ48234774 ScholiaQ48234774MaRDI QIDQ1784573

Masashi Sugiyama, Hirotaka Hachiya, Takayuki Akiyama

Publication date: 27 September 2018

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2009.12.010

zbMATH Keywords

Markov decision processreinforcement learningactive learningleast-squares policy iterationbatting robot

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Learning and adaptive systems in artificial intelligence (68T05) Algorithms for approximation of functions (65D15) Artificial intelligence for robotics (68T40)

Related Items (5)

Reward-Weighted Regression with Sample Reuse for Direct Policy Search in Reinforcement Learning ⋮ Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation ⋮ Improving importance estimation in pool-based batch active learning for approximate linear regression ⋮ Direct density-ratio estimation with dimensionality reduction via least-squares hetero-distributional subspace search ⋮ A parallel scheduling algorithm for reinforcement learning in large state space

Uses Software

• PRMLT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Active learning algorithm using the maximum weighted log-likelihood estimator
• Near-optimal reinforcement learning in polynomial time
• Adaptive importance sampling for value function approximation in off-policy reinforcement learning
• Pool-based active learning in approximate linear regression
• Robust weights and designs for biased regression models: Least squares and generalized \(M\)-estimation
• 10.1162/153244303765208377
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• 10.1162/1532443041827907
• Ridge Regression: Biased Estimation for Nonorthogonal Problems

This page was built for publication: Efficient exploration through active learning for value function approximation in reinforcement learning