Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Onyejizu, James"'
Autor:
Chen, Weiqin, Onyejizu, James, Vu, Long, Hoang, Lan, Subramanian, Dharmashankar, Kar, Koushik, Mishra, Sandipan, Paternain, Santiago
Primal-dual methods have a natural application in Safe Reinforcement Learning (SRL), posed as a constrained policy optimization problem. In practice however, applying primal-dual methods to SRL is challenging, due to the inter-dependency of the learn
Externí odkaz:
http://arxiv.org/abs/2402.00355
