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

FailureBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reinforcement LearningFailureBench Obstructed Push
Average Return1,227.18
4
Reinforcement LearningFailureBench Fragile Push Wall
Avg Return3,220.12
4
Reinforcement LearningFailureBench Bounded Soccer
Avg Return2,276.53
4
Reinforcement LearningFailureBench Bounded Push
Average Return4,593.96
4
Showing 4 of 4 rows