Rotational Walking on Real Robot TOCABI Rotational Walking
1.152Joint VelocityRegularization Reward
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Regularization Reward2025.04 | 1.152 | 0.0209 | 10.74 | 34.75 | 0.012 | |
| Regularization RewardCommand Duration (s)=5, Command Steps=1250, Random Seeds=32025.04 | 1.152 | 0.0209 | 10.74 | 34.75 | 0.012 | |
| GP-LCP2025.04 | 1.0993 | 0.0124 | 4.48 | 28.99 | 0.0062 | |
| GP-LCPCommand Duration (s)=5, Command Steps=1250, Random Seeds=32025.04 | 1.0993 | 0.0124 | 4.48 | 28.99 | 0.0062 | |
| SNλ_SN=0.22025.04 | 0.6583 | 0.0095 | 3.46 | 16.15 | 0.0154 | |
| SN$\lambda_{SN}$=0.2, Command Duration (s)=5, Command Steps=1250, Random Seeds=32025.04 | 0.6583 | 0.0095 | 3.46 | 16.15 | 0.0154 |