- Generative Multi-Adversarial Networks; I. Durugkar, I. Gemp, S. Mahadevan, Accepted in International Conference on Learning Representations, 2017
- Predictive Off-Policy Policy Evaluation for Nonstationary Decision Problems, with Applications to Digital Marketing; P. S. Thomas, G. Theocharous, M. Ghavamzadeh, I. Durugkar, E. Brunskill, in Proceedings of IAAI 2017
- Deep Generative Models for Spectroscopic Analysis on Mars; I. Gemp, I. Durugkar, M. Parente, M. Darby Dyar, S. Mahadevan ArXiv preprint arXiv:1608.05983
- Deep Reinforcement Learning with Macro-Actions I.P. Durugkar, C. Rosenbaum, S. Dernbach, S. Mahadevan, ArXiv preprint arXiv:1606.04615
- Cohort Intelligence: A Self Supervised Behavior A.J. Kulkarni, I.P. Durugkar and M.R. Kumar, in Proceedings of IEEE Systems, Man, Cybernetics Conference, Manchester, UK 2013
- Graduate Research Assistant - LARG (June 2017 - Present). Work on Reinforcement Learning with Prof. Peter Stone.
- Research Member - Autonomous Learning Lab (January 2015 - May 2017). Work on Deep RL with Prof. Sridhar Mahadevan.
- Data Scientist - UMass Alumni Association (2015-2016). Using past interactions to draw meaningful and actionable information from the alumni database.
- Research Member - OAT Research (2012 - 2013) Work on Swarm Optimization techniques for convex and non-convex problems with Dr. Anand Kulkarni.
- Research Member - MIT Tech Team (2009-2012) Robotics lab at Maharashtra Institute of Technology.
- Software Development Experience at Microsoft and Amazon.