ResearchBenchmarksReinforcement Learning on AntMaze large-diverse v2Reinforcement Learning on AntMaze large-diverse v2Follow89Online Score (1M Steps)DMG-3.5620.4744.568.53Nov 12, 2024Evaluation resultsMethodMethodLinksOnline Score (1M Steps)Offline ScoreDMGTraining Mode=offline-...Training Mode=offline-to-online fine-tuning2024.118958.8IQLTraining Mode=offline-...Training Mode=offline-to-online fine-tuning2024.1173.446TD3Training Mode=online t...Training Mode=online training from scratch2024.110—