Reinforcement Learning on Seaquest
5,000Average RewardAverage Human
Evaluation Results
| Method | Links | |
|---|---|---|
| Average Human2024.05 | 5,000 | |
| DDQN2024.05 | 3,600 | |
| DQN2024.05 | 3,500 | |
| FDQN2024.05 | 3,420 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Average Human2024.05 | 5,000 | |
| DDQN2024.05 | 3,600 | |
| DQN2024.05 | 3,500 | |
| FDQN2024.05 | 3,420 |