List your company

Continuous Control on OpenAI Gym Reacher (held-out λc ∈ {2, 3, 4})

-6.093RewardK_θ - Û
-6.73572-6.56886-6.402-6.23514Mar 2, 2026

Evaluation results

MethodLinks
K_θ - Û2026.03-6.093
K_θ2026.03-6.158
NLOT2026.03-6.173
CFM2026.03-6.251
K_I2026.03-6.307
K_I - Û2026.03-6.397
MFM2026.03-6.561
Direct2026.03-6.711