Deep Reinforcement Learning on Breakout Atari 2600
364IQM ReturnSpectral Routing
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Spectral RoutingReplay Strategy=Spectral Routing, Compute-Match status=false, Training Time (hr)=5.12026.04 | 364 | 23 | |
| REMReplay Strategy=Random Ensemble Mixture, Compute-Match status=false2026.04 | 346 | — | |
| PERReplay Strategy=Prioritized Experience Replay, Compute-Match status=false2026.04 | 340 | — | |
| Uniform ReplayReplay Strategy=Uniform, Compute-Match status=true2026.04 | 328 | — |