ResearchBenchmarksReinforcement Learning on SpaceInvadersReinforcement Learning on SpaceInvadersFollow188ReturnNSER164.08170.29176.5182.71May 10, 2026Evaluation resultsMethodMethodLinksReturnAUCSteps to τNconvΗ (η)NSERstrategy=Neuro-Symboli...strategy=Neuro-Symbolic Experience Replay2026.051885.629.251.7812.18CERstrategy=Combined Expe...strategy=Combined Experience Replay2026.051761.765.15.690.44UERstrategy=Uniform Exper...strategy=Uniform Experience Replay2026.051668.271.42.691PERstrategy=Prioritized E...strategy=Prioritized Experience Replay2026.051651.653.215.460.44