HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information

# A Self-Made Agent Based on Action-Selection

1 MAIA - Autonomous intelligent machine
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Some agents have to face multiple objectives simultaneously. In such cases, and considering partially observable environments, classical Reinforcement Learning (RL) is prone to fall in pretty low local optima, only learning straightforward behaviors. We present here a method that tries to identify and learn independent basic'' behaviors solving separate tasks the agent has to face. Using a combination of these behaviors (an action-selection algorithm), the agent is then able to efficiently deal with various complex goals in complex environments.
Mots-clés :
Document type :
Conference papers
Domain :

https://hal.inria.fr/inria-00099828
Contributor : Publications Loria Connect in order to contact the contributor
Submitted on : Tuesday, September 26, 2006 - 9:41:36 AM
Last modification on : Friday, February 26, 2021 - 3:28:05 PM

### Identifiers

• HAL Id : inria-00099828, version 1

### Citation

Olivier Buffet, Alain Dutech. A Self-Made Agent Based on Action-Selection. Sixth European Workshop on Reinforcement Learning - EWRL-6 2003, 2003, Nancy, France, pp.47-48. ⟨inria-00099828⟩

Record views