Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Ko, Byungchan"'
Autor:
Ko, Byungchan, Ok, Jungseul
Publikováno v:
Neurips2022
In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is useful for
Externí odkaz:
http://arxiv.org/abs/2206.00518
Autor:
Ko, Byungchan, Ok, Jungseul
Publikováno v:
Neurips 2022
In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is useful for
Externí odkaz:
http://arxiv.org/abs/2102.08581