| DDPG |
RL Policy learned with Deep Deterministic Policy Gradient. |
1/1 |
4.97 |
13.82 |
1.0 |
4.99 |
4.73 |
0.269 |
62.69 |
0.661 |
fwiebe |
data plot video |
| Energy Shaping and LQR |
Energy shaping for swingup and LQR for stabilization. |
1/1 |
5.18 |
13.44 |
1.0 |
4.76 |
4.09 |
0.062 |
65.11 |
0.666 |
fwiebe |
data plot video |
| Direct collocation and TVLQR |
Direct collocation trajectory stabilized with time-varying LQR. |
1/1 |
8.72 |
12.37 |
1.5 |
4.08 |
3.05 |
0.031 |
53.68 |
0.601 |
fwiebe |
data plot video |
| SAC |
RL Policy learned with Soft Actor Critic. |
1/1 |
9.61 |
10.38 |
2.0 |
12.32 |
19.44 |
1.455 |
18.55 |
0.477 |
dharnack |
data plot video |
| iLQR and TVLQR |
iLQR trajectory stabilized with time-varying LQR. |
1/1 |
5.29 |
10.66 |
1.5 |
3.66 |
2.99 |
0.024 |
40.47 |
0.701 |
fwiebe |
data plot video |
