Reinforcement Learning on Swimmer v3
359.79Mean RewardGA
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GAMode size (N)=2^82022.04 | 359.79 | 4.21 | |
| TTOptMode size (N)=32022.04 | 357.5 | 6.59 | |
| GAMode size (N)=32022.04 | 349.91 | 10.04 | |
| CMAESMode size (N)=32022.04 | 342.31 | 36.07 | |
| CMAESMode size (N)=2^82022.04 | 340.54 | 78.9 | |
| OPENESMode size (N)=32022.04 | 318.39 | 44.61 | |
| TTOptMode size (N)=2^82022.04 | 311.82 | 29.61 | |
| DACER2024.05 | 152 | — | |
| DDPG2024.05 | 146 | — | |
| SAC2024.05 | 140 | — | |
| DSAC2024.05 | 138 | — | |
| TD32024.05 | 134 | — | |
| PPO2024.05 | 130 | — | |
| OPENESMode size (N)=2^82022.04 | 109.39 | 40.11 | |
| TRPO2024.05 | 70 | — |