all AI news
CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning. (arXiv:2401.16974v1 [cs.LG])
cs.LG updates on arXiv.org arxiv.org
Causal discovery is the challenging task of inferring causal structure from
data. Motivated by Pearl's Causal Hierarchy (PCH), which tells us that passive
observations alone are not enough to distinguish correlation from causation,
there has been a recent push to incorporate interventions into machine learning
research. Reinforcement learning provides a convenient framework for such an
active approach to learning. This paper presents CORE, a deep reinforcement
learning-based approach for causal discovery and intervention planning. CORE
learns to sequentially reconstruct causal …
arxiv causation core correlation cs.lg data discovery machine machine learning reinforcement reinforcement learning research scalable