Reward-Weighted Regression with Sample Reuse for Direct Policy Search in Reinforcement Learning

DOI10.1162/NECO_a_00199zbMath1237.68147OpenAlexW1971492381WikidataQ51539172 ScholiaQ51539172MaRDI QIDQ2887009

Hirotaka Hachiya, Masashi Sugiyama, Jan Peters

Publication date: 15 May 2012

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

Full work available at URL: https://doi.org/10.1162/neco_a_00199

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Efficient Sample Reuse in Policy Gradients with Parameter-Based Exploration, Autonomous reinforcement learning with experience replay

Uses Software

• Open Dynamics Engine

Cites Work

• Improving predictive inference under covariate shift by weighting the log-likelihood function
• Adaptive importance sampling for value function approximation in off-policy reinforcement learning
• Real-time reinforcement learning by sequential actor-critics and experience replay
• Efficient exploration through active learning for value function approximation in reinforcement learning
• Using Expectation-Maximization for Reinforcement Learning
• Input-dependent estimation of generalization error under covariate shift
• Trading Variance Reduction with Unbiasedness: The Regularized Subspace Information Criterion for Robust Model Selection in Kernel Regression