On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning

Abstract

Throughout the cognitive-science literature, there is widespread agreement that decision-making agents operating in the real world do so under limited information-processing capabilities and without access to unbounded cognitive or computational resources. Prior work has drawn inspiration from this fact and leveraged an information-theoretic model of such behaviors or policies as communication channels operating under a bounded rate constraint. Meanwhile, a parallel line of work also capitalizes on the same principles from rate-distortion theory to formalize capacity-limited decision making through the notion of a learning target, which facilitates Bayesian regret bounds for provably-efficient learning algorithms. In this paper, we aim to elucidate this latter perspective by presenting a brief survey of these information-theoretic models of capacity-limited decision making in biological and artificial agents.

Cite

Text

Arumugam et al. "On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning." NeurIPS 2022 Workshops: InfoCog, 2022.

Markdown

[Arumugam et al. "On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning." NeurIPS 2022 Workshops: InfoCog, 2022.](https://mlanthology.org/neuripsw/2022/arumugam2022neuripsw-ratedistortion/)

BibTeX

@inproceedings{arumugam2022neuripsw-ratedistortion,
  title     = {{On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning}},
  author    = {Arumugam, Dilip and Ho, Mark K and Goodman, Noah and Van Roy, Benjamin},
  booktitle = {NeurIPS 2022 Workshops: InfoCog},
  year      = {2022},
  url       = {https://mlanthology.org/neuripsw/2022/arumugam2022neuripsw-ratedistortion/}
}