Reinforcement Learning on Pitfall!
6,464Final Mean PerformanceAvg. Human
Evaluation Results
| Method | Links | |
|---|---|---|
| Avg. Human2018.10 | 6,464 | |
| PPO2018.10 | 0 | |
| Dynamics2018.10 | 0 | |
| SOTA2018.10 | 0 | |
| RND2018.10 | -3 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Avg. Human2018.10 | 6,464 | |
| PPO2018.10 | 0 | |
| Dynamics2018.10 | 0 | |
| SOTA2018.10 | 0 | |
| RND2018.10 | -3 |