1 Hit in 2.2 sec

ELSIM: End-to-end learning of reusable skills through intrinsic motivation [article]

Arthur Aubret, Laetitia Matignon, Salima Hassas
2020 arXiv   pre-print
Taking inspiration from developmental learning, we present a novel reinforcement learning architecture which hierarchically learns and represents self-generated skills in an end-to-end way.  ...  To do so, we combine a previously defined mutual information objective with a novel curriculum learning algorithm, creating an unlimited and explorable tree of skills.  ...  We acknowledge the support of NVIDIA Corporation with the donation of the Titan V used for this research.  ... 
arXiv:2006.12903v1 fatcat:ojospvzwlndjjk4witdfcq5hwi