Portrait de Vedant Shah

Vedant Shah

Doctorat - UdeM
Superviseur⋅e principal⋅e
Aaron Courville
Sujets de recherche
Apprentissage de représentations
Apprentissage par renforcement
Apprentissage profond
GFlowNets
Modèles génératifs
Modèles probabilistes
Modélisation moléculaire
Raisonnement
Vision par ordinateur
Site web
Google Scholar
GitHub

Publications

Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel
Dianbo Liu
Vedant Shah
Oussama Boussif
Cristian Meo
Anirudh Goyal
Tianmin Shu
Michael Curtis Mozer
Nicolas Heess
Yoshua Bengio
In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one a… (voir plus)nother. In this paper, we propose an alternative approach whereby agents communicate through an intelligent facilitator that learns to sift through and interpret signals provided by all agents to improve the agents’ collective performance. To ensure that this facilitator does not become a centralized controller, agents are incentivized to reduce their dependence on the messages it conveys, and the messages can only influence the selection of a policy from a fixed set, not instantaneous actions given the policy. We demonstrate the strength of this architecture over existing baselines on several cooperative MARL environments.
2022-05-21
ArXiv (prépublication)
doi.org
arxiv.org