Abhinav Bhatia

CV

Updated: December 17, 2024

Download PDF

Artificial Intelligence, Reinforcement Learning, Inverse Reinforcement Learning, Real-time Planning, Robotics

Ph.D in Computer Science, University of Massachusetts, Amherst, 2025 (expected).
- Advisor: Prof. Shlomo Zilberstein
- Coursework: Artificial Intelligence, Reinforcement Learning, Robotics, Advanced Robot Dynamics & Control, Machine Learning, Neural Networks, Advanced Algorithms, Empirical Research Methods, Advanced Information Assurance
M.S. in Computer Science, University of Massachusetts, Amherst, 2022. GPA 3.95/4.
B.E. (Hons.) in Computer Science, Birla Institute of Technology and Science, Pilani, 2015. GPA 9.27/10.

Jun 2024 - Aug 2024: Applied Sciences Intern at Microsoft Xbox Game Studios, Redmond
- Worked on multi-task inverse reinforcement learning and offline reinforcement learning solutions for automated game playing.
Jun 2017 - Jul 2019: Research Engineer at School of Computing and Information Systems, Singapore Management University
- Supervised by Prof. Pradeep Varakantham and Prof. Akshat Kumar
- Worked on optimizing constrained resource allocation at city scale using deep reinforcement learning, which led to a publication.
Aug 2015 - Jun 2017: Software Engineer at Walmart Labs, Bengaluru
- Was part of Operations, Analytics & Research team for supply-chain division of Walmart’s eCommerce.
- Developed an Elasticsearch based distributed database for data analysis.
- Developed a deep-learning based system for anomaly-detection in large live incoming data streams.
Jan 2015 - Jun 2015: Software Development Engineer Intern at Amazon, Bengaluru
- Worked on offline experience for Prime Video.
- Worked on optimizing content load time for Prime Video on Kindle tablets.

Languages: Experienced in Python, Julia, C/C++, Java. Familiar with C#, SQL.
Frameworks: OpenAI Gym, PyTorch, FluxML, Tensorflow, CPLEX, Elasticsearch, Unity3D

RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$
Bhatia, A., Nashed, SB., & Zilberstein, S. (2023). In NeurIPS Workshop on Generalization in Planning. PDF
Selecting the Partial State Abstractions of MDPs: A Metareasoning Approach with Deep Reinforcement Learning
Nashed, S.B., Svegliato, J., Bhatia, A., Russell S., Zilberstein, S. (2022). In IEEE/RSJ International Conference on Intelligent Robots and Systems. PDF
Adaptive Rollout Length for Model-Based RL Using Model-Free Deep RL
Bhatia, A., Thomas, PS., & Zilberstein, S. (2022). In arXiv preprint arXiv:2206.02380. PDF
Tuning the Hyperparameters of Anytime Planning: A Metareasoning Approach with Deep Reinforcement Learning
Bhatia, A., Svegliato, J., Nashed, S. B., & Zilberstein, S. (2022). In Proceedings of the International Conference on Automated Planning and Scheduling. PDF
Tuning the Hyperparameters of Anytime Planning: A Deep Reinforcement Learning Approach
Bhatia, A., Svegliato, J., & Zilberstein, S. (2021). In ICAPS Workshop on Heuristics and Search for Domain-independent Planning. PDF
On the Benefits of Randomly Adjusting Anytime Weighted A*
Bhatia, A., Svegliato, J., & Zilberstein, S. (2021). In Proceedings of the International Symposium on Combinatorial Search. PDF
Resource Constrained Deep Reinforcement Learning
Bhatia, A., Varakantham, P., & Kumar, A. (2019). In Proceedings of the International Conference on Automated Planning and Scheduling. PDF

Teaching Assistant | CS383 Artificial Intelligence, Fall 2022
College of Information & Computer Sciences, University of Massachusetts Amherst
Responsible for designing quizzes, clarifying students’ doubts and holding office hours.

Organizing Committee member, AAAI 2024 GenPlan workshop.
Program Committee member, IJCAI 2024.
Program Committee member, NeurIPS 2023 GenPlan workshop.
Paper reviewer, JMLR, 2023.
Program Committee member, AAAI 2023.
Paper reviewer, AIJ, 2021.
As a member of IEEE BITS-Pilani chapter, conceptualized, developed and organized an AI bot making competition for a video game at college tech festival 2014.