Neural Policy Style Transfer

no code implementations • 1 Feb 2024 • Raul Fernandez-Fernandez, Juan G. Victores, Jennifer J. Gago, David Estevez, Carlos Balaguer

The implementation of three different Q-Network architectures (Shallow, Deep and Deep Recurrent Q-Network) to encode the policies within the NPST framework is proposed and the results obtained in the experiments with each of these architectures compared.

Atari Games reinforcement-learning +1

Sequence-to-Sequence Natural Language to Humanoid Robot Sign Language

no code implementations • 9 Jul 2019 • Jennifer J. Gago, Valentina Vasco, Bartek Łukawski, Ugo Pattacini, Vadim Tikhanoff, Juan G. Victores, Carlos Balaguer

Natural language to sign language translation presents several challenges to developers, such as the discordance between the length of input and output data and the use of non-manual markers.

Sign Language Translation Translation