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

MuJoCo Swimmer

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reinforcement LearningMuJoCo Swimmer v4
Normalized Performance271
18
Multi-objective Reinforcement LearningMuJoCo Swimmer
Hypervolume3.187
5
Trajectory predictionMuJoCo Swimmer (test)
Relative Error0.0122
5
Continuous control locomotionMuJoCo Swimmer v3 (train)
Average Performance161
2
Continuous ControlMuJoCo Swimmer (10M frames)
Mean Score108.27
2
Showing 5 of 5 rows