Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Donati, Alice Martin"'
Autor:
Donati, Alice Martin, Quispe, Guillaume, Ollion, Charles, Corff, Sylvain Le, Strub, Florian, Pietquin, Olivier
This paper introduces TRUncated ReinForcement Learning for Language (TrufLL), an original ap-proach to train conditional language models from scratch by only using reinforcement learning (RL). AsRL methods unsuccessfully scale to large action spaces,
Externí odkaz:
http://arxiv.org/abs/2109.09371
