Papers (α - β)
Deep meta coordination graphs for multi-agent reinforcement learningNikunj Gupta, James Z Hare, Rajgopal Kannan, Viktor PrasannaUnder submission.[PDF]
Hammer: Multi-level coordination of RL agents via learned messagingNikunj Gupta, GS Raghavan, Swarup Mohalik, Nishant Kumar, Matthew TaylorNeural Computing and Applications 2023 (Impact factor: 6.0)Previously AAMAS 2021: Adaptive and Learning Agents workshop[PDF] [Video]
CAMMARL: Conformal action modeling in multi-agent reinforcement learningNikunj Gupta, Somjit Nath, Samira Ebrahimi KahouCVPR 2023: Multi-Agent Behavior workshop[PDF]
Planning multiple epidemic interventions with reinforcement learningAnh Mai, Nikunj Gupta, Azza Abouzied, Dennis ShashaIJCAI 2023.[PDF] [Video]
On the calibration of compartmental epidemiological modelsNikunj Gupta, Anh Mai, Azza Abouzied, Dennis ShashaMaster’s Thesis @ NYU Courant, 2023.[Arxiv] [Thesis]
Prediction of drug effectiveness in rheumatoid arthritis patients using MLShengjia Chen, Nikunj Gupta, Buz Galbraith, Valay Shah, Jacopo CirroneICBBE 2022.[PDF]
Informationally-mosaic reinforcement learningNikunj Gupta, Tao Li, Quanyan ZhuPreprint 2022.[PDF]
Fully cooperative multi-agent deep reinforcement learningNikunj Gupta, GS Raghavan, Swarup MohalikMaster’s Thesis @ IIITB, 2019.[Thesis]