Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
3-Agent 6-Landmark evaluation on 3-Agent 6-Landmark Random
Loading...
470
Mean Episode Return
DOM2
129.088
217.594
306.1
394.606
Jul 4, 2023
Mean Episode Return
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Episode Return
DOM2
Environment=Standard,...
2023.07
470
OMAR
Environment=Standard,...
2023.07
326
MA-CQL
Environment=Standard,...
2023.07
321.2
DOM2
Environment=Shifted, K...
2023.07
283.7
DOM2
Environment=Shifted, K...
2023.07
262.5
MA-SfBC
Environment=Shifted, K...
2023.07
203.5
MA-SfBC
Environment=Standard,...
2023.07
198.5
MA-CQL
Environment=Shifted, K...
2023.07
186.8
OMAR
Environment=Shifted, K...
2023.07
186.7
OMAR
Environment=Shifted, K...
2023.07
178.4
MA-CQL
Environment=Shifted, K...
2023.07
177.5
MA-SfBC
Environment=Shifted, K...
2023.07
142.2
Feedback
Search any
task
Search any
task