ResearchBenchmarksPush on Push Sparse RewardFollow-4.54ReturnTQC+HER-8.4088-7.4044-6.4-5.3956Oct 8, 2024Evaluation ResultsMethodMethodLinksReturnSuccess RateTQC+HERReward structure=SparseReward structure=Sparse2024.10-4.5499.5BCReward structure=SparseReward structure=Sparse2024.10-8.1894.6DTReward structure=SparseReward structure=Sparse2024.10-8.2695