Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
Paper
• 2602.21420 • Published
• 3
Hejian Sang
pb09204048
AI & ML interests
None yet
Recent Activity
upvoted a paper about 21 hours ago
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning submitted
a paper
1 day ago
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning commented on
a paper
5 days ago
Reinforcement Learning via Self-Distillation Organizations
submitted a paper to Daily Papers 1 day ago
authored a paper about 1 month ago