Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Eisele, Artur"'
Autor:
Frauenknecht, Bernd, Eisele, Artur, Subhasish, Devdutt, Solowjow, Friedrich, Trimpe, Sebastian
Dyna-style model-based reinforcement learning (MBRL) combines model-free agents with predictive transition models through model-based rollouts. This combination raises a critical question: 'When to trust your model?'; i.e., which rollout length resul
Externí odkaz:
http://arxiv.org/abs/2405.19014
