Offline Reinforcement Learning on Kitchen Partial
90.2Normalized ScoreGCPC
Evaluation Results
| Method | Links | |
|---|---|---|
| GCPC2023.07 | 90.2 | |
| WGCSL2023.07 | 75.2 | |
| GCIQL2023.07 | 74.7 | |
| DWSL2023.07 | 74 | |
| RvS-G2023.07 | 71.7 | |
| IELPlanning Method=Sym-Graph2026.05 | 60.4 | |
| IELPlanning Method=Asym-Graph2026.05 | 60.4 | |
| IQL2023.07 | 59.7 | |
| IQLsupervision=task rewards, seeds=52023.01 | 58.8 | |
| DD2023.07 | 57 | |
| GC-IQLAlgorithm Category=ZSRL Algorithms2026.05 | 56.4 | |
| HILPPlanning Method=Rec-Mid2026.05 | 55.4 | |
| SPQRBase algorithm=CQL-Min2024.01 | 54.2 | |
| HILPPlanning Method=Sym-Graph2026.05 | 53.8 | |
| PT+%BCFramework=Preference Transformer (PT)2023.01 | 53.4 | |
| CQL2023.07 | 50.1 | |
| CQLReward Specification=Step-wise2024.02 | 49.8 | |
| CQL-Min2024.01 | 49.8 | |
| DPPOFramework=Preference Transformer (PT)2023.01 | 49.4 | |
| DPPOsupervision=preference only, seeds=52023.01 | 49.4 | |
| DT2023.07 | 48.6 | |
| IELPlanning Method=Rec-Mid2026.05 | 48.6 | |
| IQL2024.01 | 46.3 | |
| BC2023.07 | 41.3 | |
| PT+IQLFramework=Preference Transformer (PT)2023.01 | 40.2 | |
| PT+IQLsupervision=preference only, seeds=52023.01 | 40.2 | |
| Real DatasetOffline RL Algorithm=IQL, Privacy Budget (epsilon)=no-DP2025.12 | 40 | |
| BC2024.01 | 33.8 | |
| GC-CQLAlgorithm Category=ZSRL Algorithms2026.05 | 31.2 | |
| PT+RvSFramework=Preference Transformer (PT)2023.01 | 26 | |
| PrivORL-nOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.12 | 25.5 | |
| DTReward Specification=Step-wise2024.02 | 20.4 | |
| Real DatasetOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=no-DP2025.12 | 18 | |
| PT+CQLFramework=Preference Transformer (PT)2023.01 | 14.1 | |
| PT+CQLsupervision=preference only, seeds=52023.01 | 14.1 | |
| BEAR2024.01 | 13.1 | |
| CQLsupervision=task rewards, seeds=52023.01 | 12.9 | |
| PrivORL-nOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.12 | 12.5 | |
| PrivORL-nOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.12 | 11.5 | |
| DTReward Specification=Final Return2024.02 | 10.5 | |
| Real DatasetOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=no-DP2025.12 | 10 | |
| PrivORL-nOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.12 | 7.5 | |
| PATE-GANOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.12 | 4.2 | |
| PGMOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.12 | 3.5 | |
| PGMOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.12 | 2.5 | |
| PrivORL-nOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.12 | 2.5 | |
| PGMOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.12 | 2 | |
| PGMOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.12 | 2 | |
| PATE-GANOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.12 | 1.9 | |
| PGMOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.12 | 1.5 | |
| PrePATE-GANOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.12 | 0.8 | |
| PrivSynOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.12 | 0.2 | |
| SAC-Min2024.01 | 0 | |
| PGMOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.12 | 0 | |
| PrivSynOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.12 | 0 | |
| PrivSynOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.12 | 0 | |
| PrivSynOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.12 | 0 | |
| PrivSynOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.12 | 0 | |
| PrivSynOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.12 | 0 | |
| PATE-GANOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.12 | 0 | |
| PATE-GANOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.12 | 0 | |
| PATE-GANOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.12 | 0 | |
| PATE-GANOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.12 | 0 | |
| PrePATE-GANOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.12 | 0 | |
| PrePATE-GANOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.12 | 0 | |
| PrePATE-GANOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.12 | 0 | |
| PrePATE-GANOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.12 | 0 | |
| PrePATE-GANOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.12 | 0 | |
| PrivORL-nOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.12 | 0 |