Exploration of multi-state environments: Local measures and back-propagation of uncertainty
From MaRDI portal
Publication:1961327
DOI10.1023/A:1007541107674zbMath0948.68094MaRDI QIDQ1961327
Paul Bourgine, Nicolas Meuleau
Publication date: 22 November 2000
Published in: Machine Learning (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1023/a:1007541107674
68Q32: Computational learning theory
68T20: Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.)
Related Items
A novel policy based on action confidence limit to improve exploration efficiency in reinforcement learning, An asymptotically optimal policy for finite support models in the multiarmed bandit problem, A dynamic programming strategy to balance exploration and exploitation in the bandit problem