Continuous Control on Pusher v5
-30.4Final ReturnTRFP(ours)
Evaluation Results
| Method | Links | |
|---|---|---|
| TRFP(ours)NFE=4 × 42026.04 | -30.4 | |
| TRFP(one-step)NFE=1 × 42026.04 | -30.9 | |
| MaxEntDPNFE=20 × 102026.04 | -42.3 | |
| SACNFE=12026.04 | -49.6 | |
| TD3NFE=12026.04 | -60.5 | |
| SDACNFE=20 × 322026.04 | -115.4 |