VariBAD: variational bayes-adaptive deep RL via meta-learning

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

Fuld beskrivelse

Bibliografiske detaljer
Hovedforfatter: Whiteson, S
Format: Journal article
Sprog:English
Udgivet: Journal of Machine Learning Research 2021

Lignende værker