Reinforcement Learning on LunarLander v2
2,292Final Return
Advantage-weighting
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2020.12 | 2,292 | 518,153 | |
2020.12 | 278.23 | 518,153 | |
2020.12 | 272.14 | 118.9 | |
2020.12 | 266 | 121,000,000 | |
2020.12 | 262.18 | 86.9 | |
2020.12 | 258.8 | 77.6 | |
2020.12 | 254.58 | 4,337.3 | |
2020.12 | 248.221 | 632,620.2 | |
2019.10 | 229 | - | |
2020.12 | 225.79 | 1,295,307.1 | |
2020.12 | 217.92 | 210,733.2 | |
2020.12 | 217.09 | 647,691.1 | |
2020.12 | 201.47 | 1,673 | |
2020.12 | 201.46 | 30,878.1 | |
2020.12 | 201.46 | 30,878.1 | |
2020.12 | 200.65 | 259,285.8 | |
2020.12 | 200.3 | 237,079.7 | |
2020.12 | 200.22 | 30,878.1 | |
2019.10 | 185 | - | |
2020.12 | 132.83 | 136.7 | |
2019.10 | 121 | - | |
2019.10 | 104 | - | |
2020.12 | -78.4 | 89 | |
2020.12 | - | 123.3439 |