Episode Return on MABrax (ant-8x1)
3,285Episode ReturnGPAE
Evaluation Results
| Method | Links | |
|---|---|---|
| GPAESampling Protocol=off-policy, Timesteps=1 x 10^7, Random Seeds=52026.03 | 3,285 | |
| GPAESampling Protocol=on-policy, Timesteps=1 x 10^7, Random Seeds=52026.03 | 1,557 | |
| DAETimesteps=1 x 10^7, Random Seeds=52026.03 | 1,279 | |
| MAPPOTimesteps=1 x 10^7, Random Seeds=52026.03 | 1,247 | |
| COMATimesteps=1 x 10^7, Random Seeds=52026.03 | 901 |