New Study Examines Reinforcement Learning Under Runtime Confounding
A new arXiv paper explores policy learning and off-policy evaluation for reinforcement learning systems when confounding arises at runtime, with applications in healthcare, e-commerce, and robotics.
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-30 04:00 · arXiv stat.ML
Reinforcement Learning Under Runtime Confounding: Policy Learning and Off-Policy Evaluation