Continuous Control on Inverted2Pendulum v5
9,352Final ReturnSAC
Evaluation Results
| Method | Links | |
|---|---|---|
| SACNFE=12026.04 | 9,352 | |
| TD3NFE=12026.04 | 9,319.4 | |
| TRFP(ours)NFE=4 × 42026.04 | 9,304.1 | |
| TRFP(one-step)NFE=1 × 42026.04 | 9,304.1 | |
| SDACNFE=20 × 322026.04 | 8,794.3 | |
| MaxEntDPNFE=20 × 102026.04 | 8,578.2 |