Modelling bounded rational decision-making through Wasserstein constraints

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Evans, Benjamin Patrick, Ardon, Leo, Ganesh, Sumitra
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909628838707200
author Evans, Benjamin Patrick
Ardon, Leo
Ganesh, Sumitra
author_facet Evans, Benjamin Patrick
Ardon, Leo
Ganesh, Sumitra
contents Modelling bounded rational decision-making through information constrained processing provides a principled approach for representing departures from rationality within a reinforcement learning framework, while still treating decision-making as an optimization process. However, existing approaches are generally based on Entropy, Kullback-Leibler divergence, or Mutual Information. In this work, we highlight issues with these approaches when dealing with ordinal action spaces. Specifically, entropy assumes uniform prior beliefs, missing the impact of a priori biases on decision-makings. KL-Divergence addresses this, however, has no notion of "nearness" of actions, and additionally, has several well known potentially undesirable properties such as the lack of symmetry, and furthermore, requires the distributions to have the same support (e.g. positive probability for all actions). Mutual information is often difficult to estimate. Here, we propose an alternative approach for modeling bounded rational RL agents utilising Wasserstein distances. This approach overcomes the aforementioned issues. Crucially, this approach accounts for the nearness of ordinal actions, modeling "stickiness" in agent decisions and unlikeliness of rapidly switching to far away actions, while also supporting low probability actions, zero-support prior distributions, and is simple to calculate directly.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03743
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Modelling bounded rational decision-making through Wasserstein constraints
Evans, Benjamin Patrick
Ardon, Leo
Ganesh, Sumitra
Machine Learning
Artificial Intelligence
Computer Science and Game Theory
General Economics
Economics
Modelling bounded rational decision-making through information constrained processing provides a principled approach for representing departures from rationality within a reinforcement learning framework, while still treating decision-making as an optimization process. However, existing approaches are generally based on Entropy, Kullback-Leibler divergence, or Mutual Information. In this work, we highlight issues with these approaches when dealing with ordinal action spaces. Specifically, entropy assumes uniform prior beliefs, missing the impact of a priori biases on decision-makings. KL-Divergence addresses this, however, has no notion of "nearness" of actions, and additionally, has several well known potentially undesirable properties such as the lack of symmetry, and furthermore, requires the distributions to have the same support (e.g. positive probability for all actions). Mutual information is often difficult to estimate. Here, we propose an alternative approach for modeling bounded rational RL agents utilising Wasserstein distances. This approach overcomes the aforementioned issues. Crucially, this approach accounts for the nearness of ordinal actions, modeling "stickiness" in agent decisions and unlikeliness of rapidly switching to far away actions, while also supporting low probability actions, zero-support prior distributions, and is simple to calculate directly.
title Modelling bounded rational decision-making through Wasserstein constraints
topic Machine Learning
Artificial Intelligence
Computer Science and Game Theory
General Economics
Economics
url https://arxiv.org/abs/2504.03743