Reinforcement Learning on Solaris
12,380Final Mean PerformanceSOTA
Evaluation results
| Method | Links | |
|---|---|---|
| SOTAcitation=[1]2018.10 | 12,380 | |
| Avg. Human2018.10 | 12,327 | |
| PPO2018.10 | 3,387 | |
| RND2018.10 | 3,282 | |
| Dynamics2018.10 | 3,246 |
| Method | Links | |
|---|---|---|
| SOTAcitation=[1]2018.10 | 12,380 | |
| Avg. Human2018.10 | 12,327 | |
| PPO2018.10 | 3,387 | |
| RND2018.10 | 3,282 | |
| Dynamics2018.10 | 3,246 |