Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continuous Control on OpenAI Gym Reacher (held-out λc ∈ {2, 3, 4})
Loading...
-6.093
Reward
K_θ - Û
-6.73572
-6.56886
-6.402
-6.23514
Mar 2, 2026
Reward
Updated 1mo ago
Evaluation Results
Method
Method
Links
Reward
K_θ - Û
2026.03
-6.093
K_θ
2026.03
-6.158
NLOT
2026.03
-6.173
CFM
2026.03
-6.251
K_I
2026.03
-6.307
K_I - Û
2026.03
-6.397
MFM
2026.03
-6.561
Direct
2026.03
-6.711
Feedback
Search any
task
Search any
task