Reinforcement Learning on InvDoublePend
2,000,000Episodes RunDSP
Evaluation Results
| Method | Links | |
|---|---|---|
| DSP2023.11 | 2,000,000 | |
| Regression2023.11 | 1,000 | |
| ESPLSelection=Best policy of three independent runs2023.11 | 500 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| DSP2023.11 | 2,000,000 | |
| Regression2023.11 | 1,000 | |
| ESPLSelection=Best policy of three independent runs2023.11 | 500 |