Dual control for approximate Bayesian reinforcement learning (Q2834442)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Dual control for approximate Bayesian reinforcement learning |
scientific article; zbMATH DE number 6655043
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Dual control for approximate Bayesian reinforcement learning |
scientific article; zbMATH DE number 6655043 |
Statements
22 November 2016
0 references
reinforcement learning
0 references
control
0 references
Gaussian processes
0 references
filtering
0 references
Bayesian inference
0 references
stat.ML
0 references
cs.SY
0 references
math.OC
0 references
Dual control for approximate Bayesian reinforcement learning (English)
0 references
Bayesian reinforcement learning, or dual control, provides a principled solution to the exploration-exploitation trade-off for learning in interactive settings. This paper extends an old Bayesian reinforcement learning in control theory in the context of modern regression methods with ideas from contempary machine learning, including approximate Gaussian process regression and multi-layer networks. Experimental results and simple examples are also given to demonstrate the effectiveness of the proposed dual control framework.
0 references
