Error reducing sampling in reinforcement learning - Archive ouverte HAL Access content directly
Reports (Research Report) Year : 2004

Error reducing sampling in reinforcement learning


In reinforcement learning, an agent collects information interacting with an environment and uses it to derive a behavior. This paper focuses on efficient sampling; that is, the problem of choosing the interaction samples so that the corresponding behavior tends quickly to the optimal behavior. Our main result is a sensitivity analysis relating the choice of sampling any state-action pair to the decrease of an error bound on the optimal solution. We derive two new model-based algorithms. Simulations demonstrate a quicker convergence (in the sense of the number of samples) of the value function to the real optimal value function.
Fichier principal
Vignette du fichier
papier.pdf (201.35 Ko) Télécharger le fichier

Dates and versions

inria-00098352 , version 1 (25-09-2006)


  • HAL Id : inria-00098352 , version 1


Bruno Scherrer, Shie Mannor. Error reducing sampling in reinforcement learning. [Research Report] 2004, pp.15. ⟨inria-00098352⟩
66 View
61 Download


Gmail Facebook Twitter LinkedIn More