Trading utility and uncertainty: applying the value of information to resolve the exploration-exploitation dilemma in reinforcement learning

DOI10.1007/978-3-030-60990-0_19OpenAlexW3175189009MaRDI QIDQ2094051

Isaac J. Sledge, Jose C. Principe

Publication date: 28 October 2022

Full work available at URL: https://doi.org/10.1007/978-3-030-60990-0_19

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• UCB revisited: improved regret bounds for the stochastic multi-armed bandit problem
• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• Asymptotically efficient adaptive allocation rules
• Convergence results for single-step on-policy reinforcement-learning algorithms
• Pure exploration in finitely-armed and continuous-armed bandits
• Convex Optimization: Algorithms and Complexity
• Learning Theory
• Markovian Decision Processes with Uncertain Transition Probabilities
• The Nonstochastic Multiarmed Bandit Problem
• 10.1162/153244303321897663
• Asymmetry of Risk and Value of Information
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Trading utility and uncertainty: applying the value of information to resolve the exploration-exploitation dilemma in reinforcement learning