ResearchBenchmarksReinforcement Learning on Private Eye (test)Follow6.44Avg Cumulative External Reward per EpisodeSND-V0.58482.10493.6255.1451Feb 22, 2023Evaluation ResultsMethodMethodLinksAvg Cumulative External Reward per EpisodeSND-V2023.026.44SND-VIC2023.025.93SND-STD2023.023.79RND2023.022.41Baseline2023.020.81