Behavior strategy in a stationary environment with an unimprovable guaranteed mean-income convergence bound
From MaRDI portal
Publication:1185702
zbMATH Open0744.93059MaRDI QIDQ1185702FDOQ1185702
Authors: Alex V. Kolnogorov
Publication date: 28 June 1992
Published in: Automation and Remote Control (Search for Journal in Brave)
Recommendations
- A simple strategy of behavior in a stationary medium with exponential guaranteed convergence rate
- Finding minimax strategy and minimax risk in a random environment (the two-armed bandit problem)
- Publication:3479957
- Utility Functions Which Ensure the Adequacy of Stationary Strategies
- Competing with Stationary Prediction Strategies
Cited In (2)
This page was built for publication: Behavior strategy in a stationary environment with an unimprovable guaranteed mean-income convergence bound
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1185702)