Multi-task Reinforcement Learning on Atari-57 unclipped
10,700Median Human Normalised Score
PopArt-IMPALA
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2018.09 | 10,700 | |
2018.09 | 9,370 | |
2018.09 | 100 | |
2018.09 | 30 |
PopArt-IMPALA
| Method | Links | |
|---|---|---|
2018.09 | 10,700 | |
2018.09 | 9,370 | |
2018.09 | 100 | |
2018.09 | 30 |