ResearchBenchmarksGoal-conditioned policy learning on Block Push state-basedFollow97PerformanceMoDE86.689.39294.7Dec 17, 2024Evaluation ResultsMethodMethodLinksPerformanceMoDEseeds=4, history lengt...seeds=4, history length=4, action sequence length=12024.1297BESOseeds=4, history lengt...seeds=4, history length=4, action sequence length=12024.1296C-BeTseeds=4seeds=42024.1287VQ-BeTseeds=4seeds=42024.1287