artículo de publicación periódica.page.titleprefix
Training a gaming agent on brainwaves

Simple item page
dc.contributor.authorBartolomé, Francisco
dc.contributor.authorMoreno, Juan
dc.contributor.authorNavas, Natalia
dc.contributor.authorVitali, José
dc.contributor.authorRamele, Rodrigo
dc.contributor.authorSantos, Juan Miguel
dc.date.accessioned2022-06-27T15:19:39Z
dc.date.available2022-06-27T15:19:39Z
dc.date.issued2020-12-07
dc.description.abstract"Error-related potential (ErrP) are a particular type of Event-Related Potential (ERP) elicited by a person attending a recognizable error. These Electroencephalographic (EEG) signals can be used to train a gaming agent by a Reinforcement Learning (RL) algorithm to learn an optimal policy. The experimental process consists of an observational human critic (OHC) observing a simple game scenario while their brain signals are captured. The game consists of a grid, where a blue spot has to reach a desired target in the fewest amount of steps. Results show that there is an effective transfer of information and that the agent successfully learns to solve the game efficiently, from the initial 97 steps on average required to reach the target to the optimal number of 8 steps. Our results are expressed in threefold: (i) the mechanics of a simple grid-based game that can elicit the ErrP signal component, (ii) the verification that the reward function only penalizes wrong steps, which means that type II error (not properly identifying a wrong movement) does not affect significantly the agent learning process; (iii) collaborative rewards from multiple observational human critics can be used to train the algorithm effectively and can compensate low classification accuracies and a limited scope of transfer learning schemes."en
dc.identifier.urihttp://ri.itba.edu.ar/handle/123456789/3918
dc.language.isoenen
dc.relationnfo:eu-repo/semantics/altIdentifier/doi/10.1109/TG.2020.3042900
dc.relationinfo:eu-repo/grantAgreement/ITBACyT/2020-15/AR. Ciudad Autónoma de Buenos Aires
dc.subjectCEREBROes
dc.subjectJUEGOSes
dc.subjectALGORITMOSes
dc.subjectAPRENDIJZAJEes
dc.titleTraining a gaming agent on brainwavesen
dc.typeArtículos de Publicaciones Periódicases
dc.typeinfo:eu-repo/semantics/publishedVersion
dspace.entity.typeArtículo de Publicación Periódica
itba.description.filiationFil: Bartolomé, Francisco. Instituto Tecnológico de Buenos Aires; Argentina.
itba.description.filiationFil: Moreno, Juan. Instituto Tecnológico de Buenos Aires; Argentina.
itba.description.filiationFil: Navas, Natalia. Instituto Tecnológico de Buenos Aires; Argentina.
itba.description.filiationFil: Vitali, José. Instituto Tecnológico de Buenos Aires; Argentina.
itba.description.filiationFil: Ramele, Rodrigo. Instituto Tecnológico de Buenos Aires; Argentina.
itba.description.filiationFil: Santos, Juan Miguel. Instituto Tecnológico de Buenos Aires; Argentina.

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Bartolomé_2020_ING_ELECTRONICA.pdf
Size:
936.61 KB
Format:
Adobe Portable Document Format
Description:
Articulo_Bartolome
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.6 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Artículos de publicaciones periódicas