Le dilemme entre exploration et exploitation dans l'apprentissage par renforcement : optimisation adaptative des modeles de decision multi-etats

By Nicolas Meuleau. 1996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. R´emi Munos
2. Nicolas Meuleau
3. Paul Bourgine
4. Sergey Levine
5. Lihong Li
6. J. Urgen Schmidhuber
7. Bruno Scherrer
8. Amir-massoud Farahmand

Citations in the corpus

• A Study of Reinforcement Learning in the Continuous Case by the Means of Viscosity Solutions (2000, background): “…(exploration provides the system with new information about the unknown data, whereas exploitation consists in optimizing the estimated values based on the current knowledge) (see (Meuleau, 1996)), and a mechanism for integrating new information for re ning the approximation of the value function.”
• Exploration of Multi-State Environments: Local Measures and Back-Propagation of Uncertainty (1999, background): “See Meuleau (1996) for more details about parameter optimization; 2. a second set of 1000 experiments is conducted with the parameters set to their optimal value.”