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

Pusher

Benchmarks

Task NameDataset NameSOTA ResultTrend
PusherPusher
Convergence Rate100
20
Reinforcement LearningPusher
Average Returns142
16
Reinforcement LearningPusher v2
Average Final Return-19
7
Forward TransferPusher Average over Tasks 2-5
Forward Transfer (%)112
6
Forward TransferPusher Task 5
Forward Transfer Task Reward110
6
Forward TransferPusher Task 4
Forward Transfer Reward (%)105
6
Forward TransferPusher Task 3
Forward Transfer (%)109
6
Forward TransferPusher Task 2
Forward Transfer Reward138
6
Continuous ControlPusher v5
Final Return-30.4
6
PusherPusher
Metric-
0
Showing 10 of 10 rows