Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Kumar, Varun V."'
Learning and planning with latent space dynamics has been shown to be useful for sample efficiency in model-based reinforcement learning (MBRL) for discrete and continuous control tasks. In particular, recent work, for discrete action spaces, demonst
Externí odkaz:
http://arxiv.org/abs/2010.09832
