Reinforcement Learning on Qbert
7,000Average RewardAverage Human
Evaluation Results
| Method | Links | |
|---|---|---|
| Average Human2024.05 | 7,000 | |
| DDQN2024.05 | 5,200 | |
| FDQN2024.05 | 5,175 | |
| DQN2024.05 | 5,000 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Average Human2024.05 | 7,000 | |
| DDQN2024.05 | 5,200 | |
| FDQN2024.05 | 5,175 | |
| DQN2024.05 | 5,000 |