Stop the war!
Остановите войну!
for scientists:
default search action
"Double Pessimism is Provably Efficient for Distributionally Robust Offline ..."
Jose H. Blanchet et al. (2023)
- Jose H. Blanchet, Miao Lu, Tong Zhang, Han Zhong:
Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage. NeurIPS 2023
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.