Metraipolis › archive › dc_11b562efc868

Bridging Neural Tangent Kernel Analysis and Reinforcement Learning for Deep Function Approximation — arXiv:2611.03435

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03435
License (as archived)
CC0-1.0
Archived
2026-11-03T18:39:03.046Z
SHA-256 of the archived text
17e727c0c493b6eeb84d38527e2649d1a4045f402ec9991df584d8a8a3b2e122
Stable URL of this page
https://metraipolis.com/documento/dc_11b562efc868

How to cite

Bridging Neural Tangent Kernel Analysis and Reinforcement Learning for Deep Function Approximation — arXiv:2611.03435 — arXiv (en), https://arxiv.org/abs/2611.03435 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_11b562efc868 (Metraipolis archive dc_11b562efc868, sha256 17e727c0c493b6eeb84d38527e2649d1a4045f402ec9991df584d8a8a3b2e122)
BibTeX
@misc{dc11b562efc868,
  title = {Bridging Neural Tangent Kernel Analysis and Reinforcement Learning for Deep Function Approximation — arXiv:2611.03435},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03435},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_11b562efc868; sha256 17e727c0c493b6eeb84d38527e2649d1a4045f402ec9991df584d8a8a3b2e122},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03435. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Despite their widespread success across machine learning, the learning dynamics and generalization properties of neural networks remain poorly understood. The neural tangent kernel (NTK) provides an analytical characterization of the learning dynamics of infinitely wide neural networks and serves as a useful proxy for finite-width networks in supervised learning. In this work, we extend the NTK framework to reinforcement learning (RL) by introducing a temporal-difference (TD) flow formulation that accommodates time-varying mini-batches and TD targets, yielding a closed-form solution for value function evolution in an overparametrized setting. We also devise an optimization-based state-space exploration method that leverages the closed-form solution, coupled with constraints on the environment, to model the set of feasible states. On a deterministic grid environment, we validate that the proposed RL-based NTK formulation is indeed learning efficiently and adapting to the distribution shift in the training data distribution, and we demonstrate that the resulting exploration strategy improves sample efficiency. To our knowledge, this is the first work to extend NTK theory to characterize the learning dynamics of RL training with time-varying mini-batches and TD updates.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.03435 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:12:54.642Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).