Show simple item record

dc.contributor.author Daniele, Caligiore
dc.contributor.author Das, Gautham
dc.contributor.author Valerio, Sperati
dc.contributor.author Varun, Kompella
dc.contributor.author Vieri, Santucci
dc.contributor.author Benureau, Fabien
dc.contributor.author Francesco, Mannella
dc.contributor.author Mai, Nguyen
dc.contributor.author Marco, Mirolli
dc.contributor.author Vincenzo, Fiore
dc.contributor.author Gianluca, Baldassarre
dc.contributor.author Robert, Nawrocki
dc.date.accessioned 2011-09-26T09:52:13Z
dc.date.available 2011-09-26T09:52:13Z
dc.date.issued 2011-09-26
dc.identifier.citation Daniele , C , Das , G , Valerio , S , Varun , K , Vieri , S , Benureau , F , Francesco , M , Mai , N , Marco , M , Vincenzo , F , Gianluca , B & Robert , N 2011 , ' Intrinsic Motivations for Forming Actions and Producing Goal Directed Behaviour ' Paper presented at Capo Caccia Cognitive Neuromorphic Engineering Workshop , Aberystwyth , United Kingdom , 1/05/11 - 7/05/11 , . en
dc.identifier.citation conference en
dc.identifier.other PURE: 2089771
dc.identifier.other dspace: 2160/7586
dc.identifier.uri http://hdl.handle.net/2160/7586
dc.description Benureau, F., Das, G.P., Kompella, V., Nawrocki, R.A., Nguyen, S.M., Baldassarre, G., Mirolli, M., Sperati, V., Mannella, F., Fiore, V., Caligiore, D., Santucci, V. (2011). Intrinsic Motivations for Forming Actions and Producing Goal Directed Behaviour. Deliverable for the IM-CLeVeR Spring School at the Capo Caccia Cognitive Neuromorphic Engineering Workshop, 1-7 May 2011. en
dc.description.abstract In classical reinforcement learning framework, an external, handcrafted reward typically drives the learning process. Intrinsically motivated systems, on the other hand, can guide their learning process autonomously by computing the interest they have in each task they can engage in. We explore how intrinsic motivation could be implemented in the iCub platform on a learning task that was used previously with infants and monkeys, with a focus on discriminating between task of varying difficulty, and observing how their interest towards the tasks change as their knowledge of them progresses. Two main different approaches were taken : one where the reinforcement learning framework was adapted to an intrinsic reward, and another where the focus was put on a goal-oriented architecture. Two experiments settings were used, one with a console proposing buttons that activated boxes, and another proposing an interaction with rods : both experiments exhibited two tasks, one easy, and one difficult to learn. In each experiment, the system is able to successfully focus on learning the easier task earlier than the difficult one. en
dc.format.extent 7 en
dc.language.iso eng
dc.title Intrinsic Motivations for Forming Actions and Producing Goal Directed Behaviour en
dc.type Text en
dc.type.publicationtype Conference paper en
dc.contributor.institution Intelligent Robotics Group en
dc.description.status Non peer reviewed en


Files in this item

Aside from theses and in the absence of a specific licence document on an item page, all works in Cadair are accessible under the CC BY-NC-ND Licence. AU theses and dissertations held on Cadair are made available for the purposes of private study and non-commercial research and brief extracts may be reproduced under fair dealing for the purpose of criticism or review. If you have any queries in relation to the re-use of material on Cadair, contact is@aber.ac.uk.

This item appears in the following Collection(s)

Show simple item record

Search Cadair


Advanced Search

Browse

Statistics