Safe Robot Control on MuJoCo Reacher v4
-8.7Average RewardBall Chaining
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Ball ChainingChain k=9, d=496, chains=10, inner steps=402026.03 | -8.7 | 5.61 | 0.78 | 1.43 | 0 | |
| Ball ChainingChain k=8, d=496, chains=10, inner steps=402026.03 | -8.9 | 5.42 | 0.627 | 1.233 | 0 | |
| Ball ChainingChain k=7, d=496, chains=10, inner steps=402026.03 | -9 | 5.04 | 0.57 | 1.035 | 0 | |
| Ball ChainingChain k=6, d=496, chains=10, inner steps=402026.03 | -9.3 | 4.31 | 0.528 | 0.866 | 0 | |
| Ball ChainingChain k=4, d=496, chains=10, inner steps=402026.03 | -9.6 | 3.78 | 0.553 | 0.692 | 0 | |
| Ball ChainingChain k=5, d=496, chains=10, inner steps=402026.03 | -9.6 | 3.78 | 0.476 | 0.692 | 0 | |
| Ball chainingChain k=52026.03 | -9.8 | 0.007 | 0.055 | 0.305 | 0 | |
| Ball chainingChain k=62026.03 | -9.8 | 0.005 | 0.029 | 0.311 | 0 | |
| Ball chainingChain k=72026.03 | -9.8 | 0.002 | 0.021 | 0.317 | 0 | |
| Ball chainingChain k=82026.03 | -9.8 | 0.001 | 0.009 | 0.318 | 0 | |
| Ball chainingChain k=92026.03 | -9.8 | 0.001 | 0.005 | 0.319 | 0 | |
| Ball ChainingChain k=2, d=496, chains=10, inner steps=402026.03 | -9.9 | 3.74 | 0.322 | 0.406 | 0 | |
| Ball ChainingChain k=3, d=496, chains=10, inner steps=402026.03 | -9.9 | 3.69 | 0.302 | 0.456 | 0 | |
| Ball chainingChain k=42026.03 | -9.9 | 0.016 | 0.118 | 0.29 | 0 | |
| Ball chainingChain k=32026.03 | -10 | 0.029 | 0.192 | 0.25 | 0 | |
| Ball ChainingChain k=1, d=496, chains=10, inner steps=402026.03 | -10.3 | 3.84 | 0.223 | 0.23 | 0 | |
| Ball chainingChain k=22026.03 | -10.8 | 0.041 | 0.058 | 0.132 | 0 | |
| Ball chainingChain k=12026.03 | -11.2 | 0.045 | 0.068 | 0.108 | 0 | |
| Ball chainingChain k=02026.03 | -11.8 | 0.046 | 0.084 | 0.08 | 0 | |
| Ball ChainingChain k=0, d=496, chains=10, inner steps=402026.03 | -11.9 | 2.88 | 0.074 | 0.07 | 0 |