Reinforcement Learning on Hill Car MDP
56.68PerformanceAG-DPW
Evaluation results
| Method | Links | ||
|---|---|---|---|
| AG-DPWSimulations=2812025.03 | 56.68 | 0.313 | |
| AG-DPWSimulations=5002025.03 | 56.34 | 0.744 | |
| AG-DPWSimulations=892025.03 | 56.27 | 0.389 | |
| AG-VPWSimulations=5002025.03 | 44.56 | 1.028 | |
| AG-VPWSimulations=1582025.03 | 39.03 | 0.221 | |
| AG-VPWSimulations=892025.03 | 25.66 | 0.127 | |
| AG-VPWSimulations=2812025.03 | -6.36 | 0.472 | |
| AG-DPWSimulations=1582025.03 | -39.16 | 0.123 | |
| VPWSimulations=5002025.03 | -59.66 | 0.029 | |
| DPWSimulations=5002025.03 | -66.04 | 0.026 | |
| DPWSimulations=2812025.03 | -66.67 | 0.029 | |
| VPWSimulations=2812025.03 | -67.08 | 0.026 | |
| VPWSimulations=1582025.03 | -69.31 | 0.022 | |
| DPWSimulations=1582025.03 | -71.43 | 0.023 | |
| VPWSimulations=892025.03 | -90.93 | 0.008 | |
| AG-DPWSimulations=502025.03 | -91.9 | 0.036 | |
| DPWSimulations=892025.03 | -92.06 | 0.006 | |
| VPWSimulations=502025.03 | -92.71 | 0.359 | |
| DPWSimulations=502025.03 | -92.87 | 0.339 | |
| AG-VPWSimulations=502025.03 | -98.05 | 1.412 |