Dynamically Evolving Long-Term Autonomy

Dynamically Evolving Long-Term Autonomy (DELTA) is a European research project funded under the CHIST-ERA scheme (http://www.chistera.eu/).

Many complex autonomous systems (e.g., electrical distribution networks) repeatedly select actions with the aim of achieving a given objective. Reinforcement learning (RL) offers a powerful framework for acquiring adaptive behaviour in this setting, associating a scalar reward with each action and learning from experience which action to select to maximise long-term reward. Although RL has produced impressive results recently (e.g., achieving human-level play in Atari games and beating the human world champion in the board game Go), most existing solutions only work under strong assumptions: the environment model is stationary, the objective is fixed, and trials end once the objective is met.



Dept. of Information and Communication Technologies
Universitat Pompeu Fabra, Barcelona (Spain)

Roc Boronat building (Poblenou campus)
Roc Boronat, 138
08018 Barcelona

 Phone: (+34) 935422952
 Fax: (+34) 935421440

[email protected]