1 code implementation • 11 Nov 2020 • Teguh Santoso Lembono, Emmanuel Pignat, Julius Jankowski, Sylvain Calinon
We propose a generative adversarial network approach to learn the distribution of valid robot configurations under such constraints.
no code implementations • 7 Oct 2020 • Emmanuel Pignat, João Silvério, Sylvain Calinon
In particular, we show that the proposed approach can be extended to PoE with a nullspace structure (PoENS), where the model is able to recover tasks that are masked by the resolution of higher-level objectives.
no code implementations • 1 Jul 2020 • Martin Troussard, Emmanuel Pignat, Parameswaran Kamalaruban, Sylvain Calinon, Volkan Cevher
This paper proposes an inverse reinforcement learning (IRL) framework to accelerate learning when the learner-teacher \textit{interaction} is \textit{limited} during training.