Offline Meta-Reinforcement Learning on Point-Robot sampled 10 unseen (test)
-6.4Average ReturnCSRO
Evaluation Results
| Method | Links | |
|---|---|---|
| CSROnon-prior context collection strategy (Np)=true, offline RL algorithm=BRAC2023.11 | -6.4 | |
| CORROnon-prior context collection strategy (Np)=true, offline RL algorithm=BRAC2023.11 | -7.8 | |
| CSROnon-prior context collection strategy (Np)=false, offline RL algorithm=BRAC2023.11 | -9.2 | |
| CORROnon-prior context collection strategy (Np)=false, offline RL algorithm=BRAC2023.11 | -10.5 | |
| FOCALnon-prior context collection strategy (Np)=true, offline RL algorithm=BRAC2023.11 | -11.8 | |
| FOCALnon-prior context collection strategy (Np)=false, offline RL algorithm=BRAC2023.11 | -14.9 | |
| OffPearlnon-prior context collection strategy (Np)=true, offline RL algorithm=BRAC2023.11 | -17 | |
| OffPearlnon-prior context collection strategy (Np)=false, offline RL algorithm=BRAC2023.11 | -17.8 | |
| BORELnon-prior context collection strategy (Np)=true, offline RL algorithm=BRAC2023.11 | -21.6 | |
| BORELnon-prior context collection strategy (Np)=false, offline RL algorithm=BRAC2023.11 | -23.2 |