List your company

ResearchFormerly WizWand

mo-halfcheetah

Benchmarks

TaskDatasetSOTA resultTrendResults

Multi-Objective Reinforcement Learning

mo-halfcheetah v4

74.32Normalised Hypervolume (HV)

6

Multi-Objective Reinforcement Learning

mo-halfcheetah v5

22,500HV (x10^4)

6

Multi-Objective Reinforcement Learning

mo-halfcheetah MO-Gymnasium v4

0.7Hypervolume

2