ResearchBenchmarksReinforcement Learning on BreakoutReinforcement Learning on BreakoutFollow9.8ReturnNSER0.6483.0245.47.776May 10, 2026Evaluation resultsMethodMethodLinksReturnAUCSteps to τNconvη (Eta)NSERstrategy=Neuro-Symboli...strategy=Neuro-Symbolic Experience Replay2026.059.81.031.054.6420CERstrategy=Combined Expe...strategy=Combined Experience Replay2026.0543.991.032.7845UERstrategy=Uniform Exper...strategy=Uniform Experience Replay2026.053.81.917.491.39100PERstrategy=Prioritized E...strategy=Prioritized Experience Replay2026.0519.848.711.6580