ResearchBenchmarksReinforcement Learning on antmaze medium-play offline-to-onlineReinforcement Learning on antmaze medium-play offline-to-onlineFollow97.4ScoreRLPD82.8486.6290.494.18May 14, 2026Evaluation resultsMethodMethodLinksScoreRLPDEvaluation Setting=off...Evaluation Setting=offline-to-online2026.0597.4Cal-QLEvaluation Setting=off...Evaluation Setting=offline-to-online2026.0595.1CQLEvaluation Setting=off...Evaluation Setting=offline-to-online2026.0594.4CPQLEvaluation Setting=off...Evaluation Setting=offline-to-online2026.0593.4PEXEvaluation Setting=off...Evaluation Setting=offline-to-online2026.0583.4