Reinforcement Learning on Atari 2600 Venture
1,350Average ScoreRUDDER
Evaluation Results
| Method | Links | |
|---|---|---|
| RUDDERDelay (frames)=150, Delay-event=find treasure, Training game frames=200M, Number of random seeds=3, Trials per seed=10, Frame skip=42018.06 | 1,350 | |
| PPODelay (frames)=150, Delay-event=find treasure, Training game frames=200M, Number of random seeds=3, Trials per seed=10, Frame skip=42018.06 | 820 |