Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Reinforcement Learning on D4RL MuJoCo halfcheetah-medium-replay v2
Loading...
70.7
Normalized Score
ROMI
43.244
50.372
57.5
64.628
Mar 9, 2026
Normalized Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Normalized Score
ROMI
training steps=1M, see...
2026.03
70.7
COUNT
training steps=1M, see...
2026.03
70.5
RAMBO
training steps=1M, see...
2026.03
69.7
MOBILE
training steps=1M, see...
2026.03
67.7
MOPO
training steps=1M, see...
2026.03
52.1
CQL
training steps=1M, see...
2026.03
45.3
IQL
training steps=1M, see...
2026.03
44.3
Feedback
Search any
task
Search any
task