English

On the Search for Feedback in Reinforcement Learning

Machine Learning 2022-03-25 v6 Machine Learning

Abstract

The problem of Reinforcement Learning (RL) in an unknown nonlinear dynamical system is equivalent to the search for an optimal feedback law utilizing the simulations/ rollouts of the dynamical system. Most RL techniques search over a complex global nonlinear feedback parametrization making them suffer from high training times as well as variance. Instead, we advocate searching over a local feedback representation consisting of an open-loop sequence, and an associated optimal linear feedback law completely determined by the open-loop. We show that this alternate approach results in highly efficient training, the answers obtained are repeatable and hence reliable, and the resulting closed performance is superior to global state-of-the-art RL techniques. Finally, if we replan, whenever required, which is feasible due to the fast and reliable local solution, it allows us to recover global optimality of the resulting feedback law.

Keywords

Cite

@article{arxiv.2002.09478,
  title  = {On the Search for Feedback in Reinforcement Learning},
  author = {Ran Wang and Karthikeya S. Parunandi and Aayushman Sharma and Raman Goyal and Suman Chakravorty},
  journal= {arXiv preprint arXiv:2002.09478},
  year   = {2022}
}

Comments

arXiv admin note: substantial text overlap with arXiv:1904.08361

R2 v1 2026-06-23T13:49:48.996Z