Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-task Reinforcement Learning on Meta-World MT10 5 x 10^6 steps
Loading...
79
IQM
GIRL
60.28
65.14
70
74.86
Apr 8, 2026
IQM
PI
Updated 9d ago
Evaluation Results
Method
Method
Links
IQM
PI
GIRL
variant=full
2026.04
79
-
TD-MPC2
2026.04
72
35
GIRL
variant=NoGround
2026.04
69
38
GIRL
variant=FixedBeta
2026.04
67
36
DreamerV3
2026.04
61
24
Feedback
Search any
task
Search any
task
