Co-Imitation: Learning Design and Behaviour by Imitation

Chang Rajani*, David Blanco Mulero, Karol Arndt, Kevin Luck, Ville Kyrki

*Tämän työn vastaava kirjoittaja

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu


The co-adaptation of robots has been a long-standing research endeavour with the goal of adapting both body and behaviour of a system for a given task, inspired by the natural evolution of animals. Co-adaptation has the potential to eliminate costly manual hardware engineering as well as improve the performance of systems. The standard approach to co-adaptation is to use a reward function for optimizing behaviour and morphology. However, defining and constructing such reward functions is notoriously difficult and often a significant engineering effort. This paper introduces a new viewpoint on the co-adaptation problem, which we call co-imitation: finding a morphology and a policy that allow an imitator to closely match the behaviour of a demonstrator. To this end we propose a co-imitation methodology for adapting behaviour and morphology by matching state distributions of the demonstrator. Specifically, we focus on the challenging scenario with mismatched state- and action-spaces between both agents. We find that co-imitation increases behaviour similarity across a variety of tasks and settings, and demonstrate co-imitation by transferring human walking, jogging and kicking skills onto a simulated humanoid.
OtsikkoThirty-Seventh AAAI Conference on Artificial Intelligence
TilaHyväksytty/In press - 2023
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaAAAI Conference on Artificial Intelligence - Walter E. Washington Convention Center, Washington, Yhdysvallat
Kesto: 7 helmik. 202314 helmik. 2023
Konferenssinumero: 37


NimiProceedings of the AAAI Conference on Artificial Intelligence
ISSN (painettu)2159-5399
ISSN (elektroninen)2374-3468


ConferenceAAAI Conference on Artificial Intelligence


Sukella tutkimusaiheisiin 'Co-Imitation: Learning Design and Behaviour by Imitation'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä