Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
Paper
• 2602.21420 • Published
• 6
Joseph
lkdsmr
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning updated
a collection
about 8 hours ago
papers upvoted a paper about 9 hours ago
PACED: Distillation at the Frontier of Student Competence Organizations
None yet
upvoted a paper about 7 hours ago