Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MDP Planning under Reward Misspecification on Obstacles

21.12Violated Expectations Count

IRD

19.416830.913442.4153.9066Apr 12, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.04
21.12---
2024.04
42.66---
2024.04
63.7--45,026.6
2024.04
--9.6-
2024.04
-31130.3-