Virtual Tour

Assistant Professor


Education : Ph.D. (IISc Bangalore)

Raghuram Bharadwaj received his Ph.D. from the Indian Institute of Science (IISc), Bangalore, in 2022. His main research interests are in the areas of Reinforcement Learning, Deep Learning, Machine Learning, Game theory, and Multi-agent learning. He received the best student paper award at the International Joint Conference on Neural Networks (IJCNN) 2022 in Padova, Italy. His Ph.D. thesis focuses on developing reinforcement learning algorithms to solve off-policy, multi-agent problems and apply these algorithms to the smart grid setup. He received a special commendation certification in recognition of an outstanding doctoral thesis from the Department of Computer Science and Automation (CSA), IISc.  Before joining IIIT Bangalore, he was the senior data scientist at Myntra Designs Ltd., Bangalore, India, from November 2021 to November 2022.

Research Group: https://sites.google.com/view/scllab/home


Reinforcement Learning, Multi-Agent Learning, Stochastic Approximation, Deep Learning, Machine Learning, Game Theory

  • Received the IJCNN 2022 Best Student Paper award at the IEEE WCCI 2022, Italy.
  • Recipient of the Cisco CSR Ph.D. fellowship award for 2020-21 and 2019-20.
  • Received a certificate of excellence for my service as a project teaching assistant during the NMA-Deep Learning course at Neuromatch Academy.
  • Received travel grant from "Tata Trusts" to attend the Control Decision Conference, 2019 held in Nice, France.
  • Received the "Lakshmi and Aravamudan Student Travel fund" award to attend the SmartGridComm Conference, 2018 held at Aalborg, Denmark.
  • Secured AIR 47 in GATE-2014 among 1,55,190 candidates.

Recent Papers:

1. Efficient Off-Policy Algorithms for Structured Markov Decision Processes, Sourav Ganguly, Raghuram Bharadwaj Diddigi, Prabuchandran K J, (accepted for publication at) 62nd IEEE Conference on Decision and Control (CDC) 2023.

2. Autonomous UAV navigation in complex environments using human feedback, Sambhu Harimanas Karumanchi, Raghuram Bharadwaj Diddigi, Prabuchandran K J, Shalabh Bhatnagar, (accepted for publication at) 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2023). 

3. Neural network compatible off-policy natural actor-critic algorithm, Raghuram Bharadwaj Diddigi, Prateek Jain, Shalabh Bhatnagar, International Joint Conference on Neural Networks (IJCNN), 2022 (Best Student Paper award). 

Google Scholar: https://scholar.google.com/citations?user=nx4NlpsAAAAJ&hl=en

AI 705: Recommendation Systems (Jan - May 2023)

Projects and Grants:

1. Reinforcement Learning for Robotics and Large Language Models - MINRO grant

2. Explainability of Deep Reinforcement Learning - Seed grant


1. Avesha Systems

2. Ziroh Labs

Research Talks:

1. https://www.youtube.com/watch?v=Cym9toB-rYo&ab_channel=CentreforNetworkedIntelligence,IISc

2. https://www.youtube.com/watch?v=zyLWsJJ4YR4&ab_channel=CentreforNetworkedIntelligence,IISc