Preference-based reinforcement learning: a formal framework and a policy iteration algorithm

DOI10.1007/S10994-012-5313-8zbMath1260.68328OpenAlexW2154023516WikidataQ59195227 ScholiaQ59195227MaRDI QIDQ1945130

Weiwei Cheng, Johannes Fürnkranz, Sang-Hyeun Park, Eyke Hüllermeier

Publication date: 2 April 2013

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-012-5313-8

zbMATH Keywords

reinforcement learningpreference learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (7)

Preferences in artificial intelligence ⋮ A one-bit, comparison-based gradient estimator ⋮ Deterministic policies based on maximum regrets in MDPs with imprecise rewards ⋮ Preference-based reinforcement learning: evolutionary direct policy search using a preference-based racing algorithm ⋮ Global optimization based on active preference learning with radial basis functions ⋮ Active Inference: Demystified and Compared ⋮ Unnamed Item

Uses Software

• WEKA

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Efficient prediction algorithms for binary decomposition techniques
• Policy search for motor primitives in robotics
• Integrating guidance into relational reinforcement learning
• Qualitative decision theory with preference relations and comparative uncertainty: an axiomatic approach
• Natural actor-critic algorithms
• Elevator group control using multiple reinforcement learning agents
• Modeling agents as qualitative decision makers
• Learning to play chess using temporal differences
• Temporal difference learning applied to game playing and the results of application to Shogi
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Practical issues in temporal difference learning
• \({\mathcal Q}\)-learning
• Rollout sampling approximate policy iteration
• Label ranking by learning pairwise preferences
• Qualitative decision under uncertainty: back to expected utility
• Label Ranking Algorithms: A Survey
• A Survey and Empirical Comparison of Object Ranking Methods
• Preference Learning
• Stochastic Orderings for Markov Processes on Partially Ordered Spaces
• OnActor-Critic Algorithms
• Relational reinforcement learning
• Programming backgammon using self-teaching neural nets
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Preference-based reinforcement learning: a formal framework and a policy iteration algorithm