Voluntary feedback delays close a regret gap in adversarial MDPs
The method also yields the first efficient linear AMDP algorithm with regret optimal in the number of episodes K.
2 stories, newest first · one card per story
The method also yields the first efficient linear AMDP algorithm with regret optimal in the number of episodes K.
CAPS beats confirmed-answer fine-tuning by 2.6 accuracy points on Banking77 and cuts ECE by 0.053.
Today 112 readers · 115 views · 24 reads · all time 199K views