Swimmer

Benchmarks

Task Name	Dataset Name	SOTA Result
Reinforcement Learning	Swimmer	Average Returns260.35	24
Reinforcement Learning	Swimmer v3	Mean Reward359.79	15
Reinforcement Learning	Swimmer v4	Average Episodic Reward128.5	12
Locomotion	Swimmer	Relative Return Improvement3.59	10
Simulator Benchmark Optimization	Swimmer	Median Performance-339.62	9
Continuous Control	Swimmer v5	Average Episodic Reward119.3	8
Imitation Learning from Observation	Swimmer v4	AER0.73	8
Multi-objective Reinforcement Learning	Swimmer-2	Hypervolume (HV)3.54	6
Reinforcement Learning	Swimmer-vel online downstream setting	Normalized Reward1.65	6
Safe Reinforcement Learning	Swimmer-vel (offline)	Normalized Reward2.39	6
Quality-Diversity	Swimmer	GT QD Score21.31	6
Continuous Control	Swimmer v2 (test)	Average Return354	6
Imitation Learning	Swimmer	Mean Score141.1	6
Reinforcement Learning	Swimmer (Gymnasium)	Mean Best Reward294.57	5
Continuous Control	Swimmer MuJoCo v5	Max Return114	5
Reinforcement Learning	Swimmer	Mean Best Reward294.57	4
Safe Reinforcement Learning	Swimmer Velocity tasks suite	Average Reward36.32	4
Reinforcement Learning	Swimmer Velocity tasks suite (test)	Average Reward36.32	4
Robot Co-design	Swimmer search phase	D2C Score9.35	3
Continuous Control	Swimmer v5	Terminal Performance22.3	2
Reinforcement Learning	Swimmer	Terminal Performance22.3	2

Showing 21 of 21 rows