Temporal-difference (TD) learning trains neural representations using bootstrapped targets generated by evolving value estimates, yet how predictive features emerge and propagate under incomplete neural updates remains poorly understood. We investigate this problem using finite-width two-layer ReLU critics on a constru...
Shang-Zhe Li, De-Chen Zhang, Di-Fan Zou et al.· 0 citations
VALG, an agentic system that combines multi-level Verification, Adaptive formulation of Learning-theory problems, and Graph-structured proof development, is developed, an agentic system that combines multi-level Verification, adaptive formulation of Learning-theory problems, and Graph-structured proof development.
Dechen Zhang, Xuan Tang, Xinxiang Yin et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.