Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Iordan, Rares"'
Autor:
Cosier, Lucas, Iordan, Rares, Zwane, Sicelukwanda, Franzese, Giovanni, Wilson, James T., Deisenroth, Marc Peter, Terenin, Alexander, Bekiroglu, Yasemin
Publikováno v:
Artificial Intelligence and Statistics, 2024
To control how a robot moves, motion planning algorithms must compute paths in high-dimensional state spaces while accounting for physical constraints related to motors and joints, generating smooth and stable motions, avoiding obstacles, and prevent
Externí odkaz:
http://arxiv.org/abs/2309.00854
Recent progress has been made in understanding optimisation dynamics in neural networks trained with full-batch gradient descent with momentum with the uncovering of the edge of stability phenomenon in supervised learning. The edge of stability pheno
Externí odkaz:
http://arxiv.org/abs/2307.04210