Towards Min Max Generalization in Reinforcement Learning

DOI10.1007/978-3-642-19890-8_5zbMath1213.68488OpenAlexW1503631637MaRDI QIDQ3006026

Raphael Fonteneau, Damien Ernst, Louis Wehenkel, Susan A. Murphy

Publication date: 10 June 2011

Published in: Communications in Computer and Information Science (Search for Journal in Brave)

Full work available at URL: https://orbi.uliege.be/handle/2268/99584

zbMATH Keywords

finite action spacesdeterministic Lipschitz continuous environments over continuous state spacesfinite optimization horizonmin max problem

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Batch mode reinforcement learning based on the synthesis of artificial trajectories ⋮ Towards Min Max Generalization in Reinforcement Learning

Cites Work

• Performance guarantees for individualized treatment rules
• Kernel-based reinforcement learning
• Towards Min Max Generalization in Reinforcement Learning
• Percentile Optimization for Markov Decision Processes with Parameter Uncertainty
• Bias and Variance Approximation in Value Function Estimates
• Optimal Dynamic Treatment Regimes
• 10.1162/1532443041827907
• Error bounds for convolutional codes and an asymptotically optimum decoding algorithm
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item