3D on walker.stand

Metric: Return (higher is better)

LeaderboardDataset
Loading chart...
#ModelReturnAugmentationsPaperDateCode
1SMuZero987.79NoLearning and Planning in Complex Action Spaces2021-04-13Code
2MuZero Unplugged887.2NoOnline and Offline Reinforcement Learning by Pla...2021-04-13Code