Reinforcement Learning on Atari Asterix
426.9ScoreOPRIDE
Evaluation Results
| Method | Links | |
|---|---|---|
| OPRIDEObservation=pixel-based, Human-in-the-loop=true2026.02 | 426.9 | |
| IDRLObservation=pixel-based, Human-in-the-loop=true2026.02 | 357.4 | |
| OPRLObservation=pixel-based, Human-in-the-loop=true2026.02 | 164.9 | |
| PTObservation=pixel-based, Human-in-the-loop=true2026.02 | 155.8 | |
| PT+PDSObservation=pixel-based, Human-in-the-loop=true2026.02 | 146.3 |