Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Hill, Ashley"'
Autor:
Raffin, Antonin, Hill, Ashley, Traoré, René, Lesort, Timothée, Díaz-Rodríguez, Natalia, Filliat, David
Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learning, state representation learning can help learn a compact, efficient
Externí odkaz:
http://arxiv.org/abs/1901.08651
Autor:
Raffin, Antonin, Hill, Ashley, Traoré, René, Lesort, Timothée, Díaz-Rodríguez, Natalia, Filliat, David
State representation learning aims at learning compact representations from raw observations in robotics and control applications. Approaches used for this objective are auto-encoders, learning forward models, inverse dynamics or learning using gener
Externí odkaz:
http://arxiv.org/abs/1809.09369