Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Onteru, Prabhas Reddy"'
Autor:
Dukkipati, Ambedkar, Ayyagari, Ranga Shaarad, Dasgupta, Bodhisattwa, Dutta, Parag, Onteru, Prabhas Reddy
Learning agents that excel at sequential decision-making tasks must continuously resolve the problem of exploration and exploitation for optimal learning. However, such interactions with the environment online might be prohibitively expensive and may
Externí odkaz:
http://arxiv.org/abs/2412.13106
