ResearchBenchmarksReinforcement Learning on ChainReinforcement Learning on ChainFollow3,473Average ReturnEUBRL1,685.242,149.372,613.53,077.63Dec 17, 2025Evaluation resultsMethodMethodLinksAverage ReturnStandard ErrorEUBRL2025.123,47316VBRB2025.123,4652,050MBIE-EB2025.123,462—BEB2025.123,430—PSRL2025.123,15831RMAX2025.123,09036Mean-MDP2025.123,07849BOSS2025.123,003—BEETLE2025.121,754—