Barfuss, W and Mann, RP orcid.org/0000-0003-0701-1274 (2022) Modeling the effects of environmental and perceptual uncertainty using deterministic reinforcement learning dynamics with partial observability. Physical Review E: Statistical, Nonlinear, and Soft Matter Physics, 105 (3). 034409. ISSN 1539-3755
Abstract
Assessing the systemic effects of uncertainty that arises from agents' partial observation of the true states of the world is critical for understanding a wide range of scenarios, from navigation and foraging behavior to the provision of renewable resources and public infrastructures. Yet previous modeling work on agent learning and decision-making either lacks a systematic way to describe this source of uncertainty or puts the focus on obtaining optimal policies using complex models of the world that would impose an unrealistically high cognitive demand on real agents. In this work we aim to efficiently describe the emergent behavior of biologically plausible and parsimonious learning agents faced with partially observable worlds. Therefore we derive and present deterministic reinforcement learning dynamics where the agents observe the true state of the environment only partially. We showcase the broad applicability of our dynamics across different classes of partially observable agent-environment systems. We find that partial observability creates unintuitive benefits in several specific contexts, pointing the way to further research on a general understanding of such effects. For instance, partially observant agents can learn better outcomes faster, in a more stable way, and even overcome social dilemmas. Furthermore, our method allows the application of dynamical systems theory to partially observable multiagent leaning. In this regard we find the emergence of catastrophic limit cycles, a critical slowing down of the learning processes between reward regimes, and the separation of the learning dynamics into fast and slow directions, all caused by partial observability. Therefore, the presented dynamics have the potential to become a formal, yet practical, lightweight and robust tool for researchers in biology, social science, and machine learning to systematically investigate the effects of interacting partially observant agents.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2022 American Physical Society. This is an author produced version of an article published in Physical Review E: Statistical, Nonlinear, and Soft Matter Physics. Uploaded in accordance with the publisher's self-archiving policy. |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Mathematics (Leeds) > Statistics (Leeds) |
Funding Information: | Funder Grant number MRC (Medical Research Council) MR/S032525/1 |
Depositing User: | Symplectic Publications |
Date Deposited: | 04 Mar 2022 16:56 |
Last Modified: | 25 Mar 2022 20:38 |
Status: | Published |
Publisher: | American Physical Society |
Identification Number: | 10.1103/PhysRevE.105.034409 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:184121 |