List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Kitchen v0 (partial)

13.8Normalized ReturnPrivORL-j
-0.5523.1746.910.626Dec 8, 2025
Updated 8mo ago

Evaluation results

MethodLinks
PrivORL-jRL Algorithm=IQL, epsilon=102025.1213.8
PrivORL-jRL Algorithm=TD3PLUSBC, epsilon=102025.128.3
PrivORL-jRL Algorithm=IQL, epsilon=12025.127.5
PrivORL-jRL Algorithm=TD3PLUSBC, epsilon=12025.125
DP-TransformerRL Algorithm=IQL, epsilon=102025.122.5
PrivORL-j-URL Algorithm=EDAC, epsilon=12025.120
PrivORL-j-URL Algorithm=EDAC, epsilon=102025.120
DP-TransformerRL Algorithm=EDAC, epsilon=12025.120
DP-TransformerRL Algorithm=EDAC, epsilon=102025.120
PrivORL-jRL Algorithm=EDAC, epsilon=12025.120
PrivORL-jRL Algorithm=EDAC, epsilon=102025.120
PrivORL-j-URL Algorithm=IQL, epsilon=12025.120
PrivORL-j-URL Algorithm=IQL, epsilon=102025.120
DP-TransformerRL Algorithm=IQL, epsilon=12025.120
PrivORL-j-URL Algorithm=TD3PLUSBC, epsilon=12025.120
PrivORL-j-URL Algorithm=TD3PLUSBC, epsilon=102025.120
DP-TransformerRL Algorithm=TD3PLUSBC, epsilon=12025.120
DP-TransformerRL Algorithm=TD3PLUSBC, epsilon=102025.120