Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continuous Control on DeepMind Control Suite (IQM Aggregation)
Loading...
806.21
Cartpole Swingup IQM
PPO
777.6204
785.0427
792.465
799.8873
Feb 6, 2026
Cartpole Swingup IQM
Cheetah Run IQM
Hopper Hop IQM
Humanoid Walk IQM
Walker Walk IQM
Mean IQM
Updated 3mo ago
Evaluation Results
Method
Method
Links
Cartpole Swingup IQM
Cheetah Run IQM
Hopper Hop IQM
Humanoid Walk IQM
Walker Walk IQM
Mean IQM
PPO
Number of seeds=9
2026.02
806.21
513.1
0.91
1.98
656.94
395.83
TRPO
Number of seeds=9
2026.02
804.93
429.83
0.57
1.47
550.04
357.37
BTRPO
Number of seeds=9
2026.02
799.39
441.62
0.69
1.88
626.75
374.07
BPPO
Number of seeds=9
2026.02
778.72
513.22
13.23
2.1
673.23
396.1
Feedback
Search any
task
Search any
task
