Uncertainty Propagation for Efficient Exploration in Reinforcement Learning

DOI10.3233/978-1-60750-606-5-361MaRDI QIDQ2999161zbMATH OpenOpenAlexFDO

Authors Alexander Hans, Steffen Udluft

Publication date 11 May 2011

Full work available at URL https://doi.org/10.3233/978-1-60750-606-5-361

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Applications of statistics (62P99)

Recommendations

• A model for system uncertainty in reinforcement learning
• Exploration of multi-state environments: Local measures and back-propagation of uncertainty
• 10.1162/153244303321897663
• Bayesian Reinforcement Learning with Exploration
• Active policy learning for robot planning and exploration under uncertainty
• Trading utility and uncertainty: applying the value of information to resolve the exploration-exploitation dilemma in reinforcement learning
• Deep exploration via randomized value functions

Cited in

(8)

• Trading utility and uncertainty: applying the value of information to resolve the exploration-exploitation dilemma in reinforcement learning
• A model for system uncertainty in reinforcement learning
• scientific article; zbMATH DE number 2063052 (Why is no real title available?)
• Exploration of multi-state environments: Local measures and back-propagation of uncertainty
• Guiding exploration by pre-existing knowledge without modifying reward
• Uncertainty quantification and exploration for reinforcement learning
• A reinforcement learning algorithm based on information entropy
• A novel policy based on action confidence limit to improve exploration efficiency in reinforcement learning

Describes a project that uses

Uses Software

• R-MAX

This page was built for publication: Uncertainty Propagation for Efficient Exploration in Reinforcement Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2999161)