Deep Reinforcement Learning on Pong Atari 2600
19.8IQM ReturnSpectral Routing
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Spectral RoutingReplay Strategy=Spectral Routing, Compute-Match status=false, Training Time (hr)=4.82026.04 | 19.8 | 2 | |
| REMReplay Strategy=Random Ensemble Mixture, Compute-Match status=false2026.04 | 19.6 | — | |
| PERReplay Strategy=Prioritized Experience Replay, Compute-Match status=false2026.04 | 19.5 | — | |
| Uniform ReplayReplay Strategy=Uniform, Compute-Match status=true2026.04 | 19.3 | — |