ResearchBenchmarksMulti-task Reinforcement Learning on DIBS Multi-environment Suite Unseen tasksMulti-task Reinforcement Learning on DIBS Multi-environment Suite Unseen tasksFollow14.04Relative Solved Ratio (vs DIBS)MAML2.65.578.5411.51May 30, 2026Evaluation resultsMethodMethodLinksRelative Solved Ratio (vs DIBS)MAML2026.0514.04GenRL2026.056.19VariBAD2026.053.04