Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Comparison of MOMDP and heuristic methods to play hide-and-seek

Autor
Goldhoorn, A.; Sanfeliu, A.; Alquezar, R.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
16th International Conference of the Catalan Association for Artificial Intelligence
Any de l'edició
2013
Data de presentació
2013-10-23
Llibre d'actes
Artificial intelligence research and development: proceedings of the 16th International Conference of the Catalan Association for Artificial Intelligence
Pàgina inicial
31
Pàgina final
40
DOI
10.3233/978-1-61499-320-9-31
URL
http://dx.doi.org/10.3233/978-1-61499-320-9-31 Obrir en finestra nova
Resum
The hide-and-seek game is considered an excellent domain for studying the interactions between mobile robots and humans. Prior to the implementation and test in our mobile robots TIBI and DABO, we have been devising different models and strategies to play this game and comparing them extensively in simulations. Recently, we have proposed the use of MOMDP (Mixed Observability Markov Decision Processes) models to learn a good policy to be applied by the seeker. Even though MOMDPs reduce the comput...
Paraules clau
POMDP, hide-and-Seek, human robot interaction, robotics
Grup de recerca
SOCO - Soft Computing
VIS - Visió Artificial i Sistemes Intel.ligents

Participants