List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on VD4RL Cheetah-run pixel-based (medium-replay)

61.6Normalized ScoreOffline DV2
24.1633.8843.653.32May 27, 2024Jun 23, 2024Jul 20, 2024Aug 17, 2024Sep 13, 2024Oct 10, 2024Nov 7, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Offline DV2Implementation Source=Original Paper Results [20]2024.1161.6
Offline DV2Implementation Source=This Paper Re-implementation2024.1154.6
C-LAPImplementation Source=This Paper2024.1152.5
DrQ+BCAugmentation=None2024.0544.8
LOMPOImplementation Source=This Paper Re-implementation2024.1142.2
GTABase Algorithm=DrQ+BC, Augmentation=GTA2024.0538.1
LOMPOImplementation Source=Original Paper Results [20]2024.1136.3
DrQ+BCAugmentation=SynthER2024.0525.6