List your company

ResearchFormerly WizWand

Deep Sea Treasure

Benchmarks

TaskDatasetSOTA resultTrendResults

Multi-Objective Reinforcement Learning

Deep Sea Treasure

22,845.4Hypervolume (HV)

10

Multi-Objective Reinforcement Learning

deep-sea-treasure v0

0.542Normalised Hypervolume (HV)

4

Multi-objective Offline Reinforcement Learning

Deep Sea Treasure

15ND

2