TFE 2009-2010 (final year project)

Development of a new generation of reinforcement learning agents having much better learning capabilities

Reinforcement Learning (RL) refers to a class of problems which postulate an artificial intelligent agent exploring an environment in which the agent perceives information about its current state and takes actions. The environment, in return, provides a reward signal. The agent has as objective to maximize the cumulative reward signal over the course of the interaction. RL agents have been successfully used to solve problems in various fields such as finance, engineering, video games or medicine.

The goal of this project is to collaborate with researchers active in the field of RL on the development of a new generation of RL agents having much better learning capabilities.

Renseignements, Promoteur: