English

Towards neural reinforcement learning for large deviations in nonequilibrium systems with memory

Statistical Mechanics 2026-03-09 v2

Abstract

We introduce a reinforcement learning method for a class of non-Markov systems; our approach extends the actor-critic framework given by Rose et al. [New J. Phys. 23 013013 (2021)] for obtaining scaled cumulant generating functions characterizing the fluctuations. The actor-critic is implemented using neural networks; a particular innovation in our method is the use of an additional neural policy for processing memory variables. We demonstrate results for current fluctuations in various memory-dependent models with special focus on semi-Markov systems where the dynamics is controlled by nonexponential interevent waiting time distributions.

Keywords

Cite

@article{arxiv.2501.12333,
  title  = {Towards neural reinforcement learning for large deviations in nonequilibrium systems with memory},
  author = {Venkata D. Pamulaparthy and Rosemary J. Harris},
  journal= {arXiv preprint arXiv:2501.12333},
  year   = {2026}
}

Comments

48 pages, 16 figures. Accepted in JSTAT

R2 v1 2026-06-28T21:12:43.194Z