Discrete Decision-Making on Arcade Learning Environment Atari 43 Games
100TD3 Normalized ScoreDreamerV3
Evaluation results
| Method | Links | |
|---|---|---|
| DreamerV3Observation Space=Pixel, Action Space=Discrete, Training Steps=2.5M steps2026.02 | 100 | |
| ULDObservation Space=Pixel, Action Space=Discrete, Training Steps=2.5M steps2026.02 | 94 | |
| PPOObservation Space=Pixel, Action Space=Discrete, Training Steps=2.5M steps2026.02 | 82 | |
| TD-MPC2Observation Space=Pixel, Action Space=Discrete, Training Steps=2.5M steps2026.02 | 78 |