Continuous Control on cheetah.run

Metric: Return (higher is better)

LeaderboardDataset
Loading chart...
#ModelReturnExtra DataPaperDateCode
1SMuZero914.39NoLearning and Planning in Complex Action Spaces2021-04-13Code
2MuZero Unplugged869.9NoOnline and Offline Reinforcement Learning by Pla...2021-04-13Code