#RACER

2 stories · 0 in 7 days · 0 in 30 days

learning to defer 1 human-AI collaboration 1 reinforcement learning 1 robustness 1

Stories, products and papers tagged "RACER", newest first.

Sep 24

Papers Builders09:37

Chinese contentRACER：用风险敏感目标与Critic一致性正则改进对抗强化学习

做强化学习的可以看看：RACER 用自适应扰动和 critic 一致性正则，解决了对抗训练里对手太狠把智能体带偏的问题，连续控制实验效果确实比老基线稳。

#RACER #reinforcement learning #robustness

arXiv cs.LG@Jiaxi Wu et al. (5)Source

Sep 21

Papers BuildersSelected11:15

RACER Framework Routes Queries Between AI Models and Human Experts

Compared with L2D-Pop and IFD, RACER captures instance-level expert specialization without class-identity shortcuts, a practical design for medical AI triage systems that must route chest X-rays between models and radiologists.

#RACER #learning to defer #human-AI collaboration

arXiv cs.LG@Joshua Strong et al. (6)Source