Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Heterogeneous Pendulum

Benchmarks

Task NameDataset NameSOTA ResultTrend
Offline ControlHeterogeneous Pendulum Rich-Data 600,000 transition steps
Cumulative Reward-0.6
7
Offline ControlHeterogeneous Pendulum 300,000 transition steps (Mid-Data)
Cumulative Reward-1.25
7
Offline ControlHeterogeneous Pendulum Low-Data 100,000 transition steps
Cumulative Reward-1.39
7
Showing 3 of 3 rows