Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
3-Agent 6-Landmark on 3-Agent 6-Landmark Expert
Loading...
683.3
Mean Episode Return
DOM2
241.092
355.896
470.7
585.504
Jul 4, 2023
Mean Episode Return
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Episode Return
DOM2
Environment=Standard,...
2023.07
683.3
MA-SfBC
Environment=Standard,...
2023.07
606.1
OMAR
Environment=Standard,...
2023.07
595
DOM2
Environment=Shifted, K...
2023.07
487.6
MA-SfBC
Environment=Shifted, K...
2023.07
470.6
MA-CQL
Environment=Standard,...
2023.07
457.5
DOM2
Environment=Shifted, K...
2023.07
393.1
MA-SfBC
Environment=Shifted, K...
2023.07
374.2
OMAR
Environment=Shifted, K...
2023.07
358.2
OMAR
Environment=Shifted, K...
2023.07
334
MA-CQL
Environment=Shifted, K...
2023.07
277.7
MA-CQL
Environment=Shifted, K...
2023.07
258.1
Feedback
Search any
task
Search any
task