Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Meta-Reinforcement Learning on Point-Robot sampled 10 unseen (test)
Loading...
-6.4
Average Return
CSRO
-23.872
-19.336
-14.8
-10.264
Nov 7, 2023
Average Return
Updated 4d ago
Evaluation Results
Method
Method
Links
Average Return
CSRO
non-prior context coll...
2023.11
-6.4
CORRO
non-prior context coll...
2023.11
-7.8
CSRO
non-prior context coll...
2023.11
-9.2
CORRO
non-prior context coll...
2023.11
-10.5
FOCAL
non-prior context coll...
2023.11
-11.8
FOCAL
non-prior context coll...
2023.11
-14.9
OffPearl
non-prior context coll...
2023.11
-17
OffPearl
non-prior context coll...
2023.11
-17.8
BOREL
non-prior context coll...
2023.11
-21.6
BOREL
non-prior context coll...
2023.11
-23.2
Feedback
Search any
task
Search any
task