List your company

Deep Reinforcement Learning on Montezuma's Revenge Atari 2600

0IQM ReturnUniform Replay
-0.001-0.000500.0005Apr 15, 2026

Evaluation results

MethodLinks
Uniform ReplayReplay Strategy=Uniform, Compute-Match status=true2026.040—
PERReplay Strategy=Prioritized Experience Replay, Compute-Match status=false2026.040—
REMReplay Strategy=Random Ensemble Mixture, Compute-Match status=false2026.040—
Spectral RoutingReplay Strategy=Spectral Routing, Compute-Match status=false, Training Time (hr)=5.52026.0401