Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Adaptation on Point-Maze Shift (meta-test)
Loading...
-5.37
Average Return
Expert
-30.694
-24.1195
-17.545
-10.9705
Sep 20, 2019
Average Return
Updated 3mo ago
Evaluation Results
Method
Method
Links
Average Return
Expert
Type=Oracle/Ground Truth
2019.09
-5.37
PEMIRL
Task Mode=Reward Adapt...
2019.09
-9.04
AIRL
Task Mode=Reward Adapt...
2019.09
-29.07
Meta-InfoGAIL
Task Mode=Reward Adapt...
2019.09
-29.72
Feedback
Search any
task
Search any
task