Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Adaptation on Disabled-Ant (meta-test)
Loading...
331.17
Average Return
Expert
-92.5052
17.4874
127.48
237.4726
Sep 20, 2019
Average Return
Updated 3mo ago
Evaluation Results
Method
Method
Links
Average Return
Expert
Type=Oracle/Ground Truth
2019.09
331.17
PEMIRL
Task Mode=Reward Adapt...
2019.09
152.62
Meta-InfoGAIL
Task Mode=Reward Adapt...
2019.09
-38.73
AIRL
Task Mode=Reward Adapt...
2019.09
-76.21
Feedback
Search any
task
Search any
task