Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continuous control locomotion on MuJoCo Walker2d v3 (train)
Loading...
2,199
Avg Return (1M Steps)
GePPO
1,801.72
1,904.86
2,008
2,111.14
Oct 29, 2021
Avg Return (1M Steps)
Final Return
Steps (M) to Final PPO
Percent Improvement
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg Return (1M Steps)
Final Return
Steps (M) to Final PPO
Percent Improvement
GePPO
clipping parameter=0.1...
2021.10
2,199
3,502
0.63
21
PPO
clipping parameter=0.2...
2021.10
1,817
3,041
1
-
Feedback
Search any
task
Search any
task
