Repository logo
Research Data
Publications
Projects
Persons
Organizations
English
Français
Log In(current)
  1. Home
  2. Publications
  3. Article de recherche (journal article)
  4. Risk-Sensitive Bayesian Games for Multi-Agent Reinforcement Learning under Policy Uncertainty

Risk-Sensitive Bayesian Games for Multi-Agent Reinforcement Learning under Policy Uncertainty

Author(s)
Hannes Eriksson
Debabrota Basu
Mina Alibeigi
Dimitrakakis, Christos  
Chaire de science des données  
Date issued
March 18, 2022
Number of pages
5 pages, 1 figure, 2 tables
Subjects
Machine Learning (cs.LG) Multiagent Systems (cs.MA)
Abstract
In stochastic games with incomplete information, the uncertainty is evoked by the lack of knowledge about a player's own and the other players' types, i.e. the utility function and the policy space, and also the inherent stochasticity of different players' interactions. In existing literature, the risk in stochastic games has been studied in terms of the inherent uncertainty evoked by the variability of transitions and actions. In this work, we instead focus on the risk associated with the \textit{uncertainty over types}. We contrast this with the multi-agent reinforcement learning framework where the other agents have fixed stationary policies and investigate risk-sensitiveness due to the uncertainty about the other agents' adaptive policies. We propose risk-sensitive versions of existing algorithms proposed for risk-neutral stochastic games, such as Iterated Best Response (IBR), Fictitious Play (FP) and a general multi-objective gradient approach using dual ascent (DAPG). Our experimental analysis shows that risk-sensitive DAPG performs better than competing algorithms for both social welfare and general-sum stochastic games.
Publication type
journal article
Identifiers
https://libra.unine.ch/handle/20.500.14713/64441
DOI
10.48550/arXiv.2203.10045
-
2203.10045v1
-
https://libra.unine.ch/handle/123456789/30951
File(s)
Loading...
Thumbnail Image
Download
Name

2203.10045.pdf

Type

Main Article

Size

559.74 KB

Format

Adobe PDF

Checksum

(MD5):5d7fa7b5566bcc427bad7800f43efc66

Université de Neuchâtel logo

Service information scientifique & bibliothèques

Rue Emile-Argand 11

2000 Neuchâtel

contact.libra@unine.ch

Service informatique et télématique

Rue Emile-Argand 11

Bâtiment B, rez-de-chaussée

Powered by DSpace-CRIS

v2.0.0

© 2025 Université de Neuchâtel

Portal overviewUser guideOpen Access strategyOpen Access directive Research at UniNE Open Access ORCIDWhat's new