Reinforcement Learning on Pacman
10,000Average RewardAverage Human
Evaluation Results
| Method | Links | |
|---|---|---|
| Average Human2024.05 | 10,000 | |
| DDQN2024.05 | 6,300 | |
| FDQN2024.05 | 6,150 | |
| DQN2024.05 | 6,000 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Average Human2024.05 | 10,000 | |
| DDQN2024.05 | 6,300 | |
| FDQN2024.05 | 6,150 | |
| DQN2024.05 | 6,000 |