VariBAD: a very good method for Bayes-adaptive deep RL via meta-learning

VariBAD: a very good method for Bayes-adaptive deep RL via meta-learning

Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning. A Bayes-optimal policy, which does so optimally, conditions its actions not only on the environment state but on the agent’s uncertainty about the environment. Computing a Bayes-o...

Ful tanımlama

Detaylı Bibliyografya
Asıl Yazarlar: Zintgraf, L, Shiarlis, K, Igl, M, Schulze, S, Gal, Y, Hofmann, K, Whiteson, S
Materyal Türü: Conference item
Dil:English
Baskı/Yayın Bilgisi: International Conference on Learning Representations 2020

Benzer Materyaller

Benzer Materyaller