Logo du site
  • English
  • Français
  • Se connecter
Logo du site
  • English
  • Français
  • Se connecter
  1. Accueil
  2. Université de Neuchâtel
  3. Publications
  4. Risk-Sensitive Bayesian Games for Multi-Agent Reinforcement Learning under Policy Uncertainty
 
  • Details
Options
Vignette d'image

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

Auteur(s)
Hannes Eriksson
Debabrota Basu
Mina Alibeigi
Dimitrakakis, Christos 
Institut d'informatique 
Date de parution
2022-03-18T16:40:30Z
Nombre de page
5 pages, 1 figure, 2 tables
Mots-clés
  • Machine Learning (cs.LG)
  • Multiagent Systems (cs.MA)
  • Machine Learning (cs....

  • Multiagent Systems (c...

Résumé
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.
Identifiants
https://libra.unine.ch/handle/123456789/30951
_
10.48550/arXiv.2203.10045
_
2203.10045v1
Type de publication
journal article
Dossier(s) à télécharger
 main article: 2203.10045.pdf (559.74 KB)
google-scholar
Présentation du portailGuide d'utilisationStratégie Open AccessDirective Open Access La recherche à l'UniNE Open Access ORCIDNouveautés

Service information scientifique & bibliothèques
Rue Emile-Argand 11
2000 Neuchâtel
contact.libra@unine.ch

Propulsé par DSpace, DSpace-CRIS & 4Science | v2022.02.00