Dayan, P; Sejnowski, TJ; (1996) Exploration bonuses and dual control. MACH LEARN , 25 (1) 5 - 22.
Full text not available from this repository.
Finding the Bayesian balance between exploration and exploitation in adaptive optimal control is in general intractable. This paper shows how to compute suboptimal estimates based on a certainty equivalence approximation (Cozzolino, Gonzalez-Zubieta & Miller, 1965) arising from a form of dual control. This systematizes and extends existing uses of exploration bonuses in reinforcement learning (Sutton, 1990). The approach has two components: a statistical model of uncertainty in the world and a way of turning this into exploratory behavior. This general approach is applied to two-dimensional mazes with moveable barriers and its performance is compared with Sutton's DYNA system.
|Title:||Exploration bonuses and dual control|
|Keywords:||reinforcement learning, dynamic programming, exploration bonuses, certainty equivalence, nonstationary environment, TIME|
|UCL classification:||UCL > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neuroscience Unit|
Archive Staff Only: edit this record