Astrid Vanneste

Astrid Vanneste

Auto-generated profile, based on publicly available information

Astrid Vanneste

University of Antwerp - imec

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 October 2021
Verified
Book Chapter
Closed access
PDF file
AVAstrid Vanneste
Astrid Vanneste
WWWesley Van Wijnsberghe
Wesley Van Wijnsberghe
SVSimon Vanneste
Simon Vanneste
KMKevin Mets
Kevin Mets
SMSiegfried Mercelis
Siegfried Mercelis
PHPeter Hellinckx
Peter Hellinckx

20 October 2019
Verified
Book Chapter
Closed access
PDF file
SVSimon Vanneste
Simon Vanneste
AVAstrid Vanneste
Astrid Vanneste
SBStig Bosmans
Stig Bosmans
SMSiegfried Mercelis
Siegfried Mercelis
PHPeter Hellinckx
Peter Hellinckx

10 January 2025 in Neural Computing and Applications
Verified
Journal Article
Open access
PDF file
SVSimon Vanneste
Simon Vanneste
AVAstrid Vanneste
Astrid Vanneste
KMKevin Mets
Kevin Mets
TSTom De Schepper
Tom De Schepper
AAAli Anwar
Ali Anwar
PHPeter Hellinckx
Peter Hellinckx
Learning to communicate in order to share state information is an active problem in the area of multi-agent reinforcement learning. The credit assignment problem, the non-stationarity of the communication environment and the problem of encouraging the agents to be influenced by incoming messages are major challenges within this research field which need to be overcome in order to learn a valid communication protocol. This paper introduces the novel multi-agent counterfactual communication learning (MACC) method which adapts counterfactual reasoning in order to overcome the credit assignment problem for communicating agents. Next, the non-stationarity of the communication environment, while learning the communication Q-function, is overcome by creating the communication Q-function using the action policy of the other agents and the Q-function of the action environment. As the exact method to create the communication Q-function can be computationally intensive for a large number of agents, two approximation methods are proposed. Additionally, a social loss function is introduced in order to create influenceable agents, which is required to learn a valid communication protocol. Our experiments show that MACC is able to outperform the state-of-the-art baselines in four different scenarios in the particle environment. Finally, we demonstrate the scalability of MACC in a matrix environment.

2 November 2024
Verified
Book Chapter
Closed access
PDF file
SVSimon Vanneste
Simon Vanneste
AVAstrid Vanneste
Astrid Vanneste
TSTom De Schepper
Tom De Schepper
SMSiegfried Mercelis
Siegfried Mercelis
PHPeter Hellinckx
Peter Hellinckx
KMKevin Mets
Kevin Mets

13 May 2026 in Neural Computing and Applications
Verified
Journal Article
Open access
AVAstrid Vanneste
Astrid Vanneste
SVSimon Vanneste
Simon Vanneste
TSTom De Schepper
Tom De Schepper
SMSiegfried Mercelis
Siegfried Mercelis
PHPeter Hellinckx
Peter Hellinckx
KMKevin Mets
Kevin Mets

26 April 2022 in arXiv
Verified
Preprint
Open access
PDF file
SVSimon Vanneste
Simon Vanneste
AVAstrid Vanneste
Astrid Vanneste
KMKevin Mets
Kevin Mets
TSTom De Schepper
Tom De Schepper
AAAli Anwar
Ali Anwar
PHPeter Hellinckx
Peter Hellinckx
Learning to communicate in order to share state information is an active problem in the area of multi-agent reinforcement learning (MARL). The credit assignment problem, the non-stationarity of the communication environment and the creation of influenceable agents are major challenges within this research field which need to be overcome in order to learn a valid communication protocol. This paper introduces the novel multi-agent counterfactual communication learning (MACC) method which adapts counterfactual reasoning in order to overcome the credit assignment problem for communicating agents. Secondly, the non-stationarity of the communication environment while learning the communication Q-function is overcome by creating the communication Q-function using the action policy of the other agents and the Q-function of the action environment. Additionally, a social loss function is introduced in order to create influenceable agents which is required to learn a valid communication protocol. Our experiments show that MACC is able to outperform the state-of-the-art baselines in four different scenarios in the Particle environment.