3D on walker.walk

Metric: Return (higher is better)

LeaderboardDataset
Loading chart...
#ModelReturnAugmentationsPaperDateCode
1SMuZero975.46NoLearning and Planning in Complex Action Spaces2021-04-13Code
2MuZero Unplugged949.5NoOnline and Offline Reinforcement Learning by Pla...2021-04-13Code