@InProceedings{pmlr-v242-jongeneel24a,
  title = 	 {A large deviations perspective on policy gradient algorithms},
  author =       {Jongeneel, Wouter and Kuhn, Daniel and Li, Mengmeng},
  booktitle = 	 {Proceedings of the 6th Annual Learning for Dynamics & Control Conference},
  pages = 	 {916--928},
  year = 	 {2024},
  editor = 	 {Abate, Alessandro and Cannon, Mark and Margellos, Kostas and Papachristodoulou, Antonis},
  volume = 	 {242},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {15--17 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v242/jongeneel24a/jongeneel24a.pdf},
  url = 	 {https://proceedings.mlr.press/v242/jongeneel24a.html},
  abstract = 	 {Motivated by policy gradient methods in the context of reinforcement learning, we derive the first large deviation rate function for the iterates generated by stochastic gradient descent for possibly non-convex objectives satisfying a Polyak-Łojasiewicz condition. Leveraging the contraction principle from large deviations theory, we illustrate the potential of this result by showing how convergence properties of policy gradient with a softmax parametrization and an entropy regularized objective can be naturally extended to a wide spectrum of other policy parametrizations.}
}