Metric: Human World Record Breakthrough (higher is better)
| # | Model↕ | Human World Record Breakthrough▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GDI-H3 | 22 | No | Generalized Data Distribution Iteration | 2022-06-07 | - |
| 2 | Muzero | 19 | No | Mastering Atari, Go, Chess and Shogi by Planning... | 2019-11-19 | Code |
| 3 | Agent57 | 18 | No | Agent57: Outperforming the Atari Human Benchmark | 2020-03-30 | Code |
| 4 | Go-Explore | 17 | No | Go-Explore: a New Approach for Hard-Exploration ... | 2019-01-30 | Code |
| 5 | GDI-I3 | 17 | No | Generalized Data Distribution Iteration | 2022-06-07 | - |
| 6 | R2D2 | 15 | No | - | - | Code |
| 7 | NGU | 8 | No | Never Give Up: Learning Directed Exploration Str... | 2020-02-14 | Code |
| 8 | Muesli | 5 | No | Muesli: Combining Improvements in Policy Optimiz... | 2021-04-13 | Code |
| 9 | Rainbow | 4 | No | Rainbow: Combining Improvements in Deep Reinforc... | 2017-10-06 | Code |