Featured publications

Periodic agent-state based Q-learning for POMDPs (arxiv) (pdf)
Amit Sinha, Matthieu Geist, and Aditya Mahajan
Conference on Neural Information Processing Systems (Neurips), Dec 2024.
Agent-state based policies in POMDPs: Beyond belief-state MDPs (pdf)
Amit Sinha and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Dec 2024.
Approximate information state for approximate planning and reinforcement learning in partially observed systems (pdf) (code)
Jayakumar Subramanian, Amit Sinha, Raihan Seraj, and Aditya Mahajan
Journal of Machine Learning Research, vol. 23, no. 12, pp. 1-83, Feb 2022.
URL: https://www.jmlr.org/papers/v23/20-1165.html

List of other publications

Asymmetric Actor Critic with Approximate Information State (pdf)
Amit Sinha and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Dec 2023.
Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning (pdf)
Hadi Nekoei, Akilesh Badrinaaraayanan, Amit Sinha, Mohammad Amini, Janarthanan Rajendran, Aditya Mahajan, and Sarath Chandar
Conference on Lifelong Learning Agents (CoLLA), Aug 2023.
Approximate information state based convergence analysis of recurrent Q-learning (arxiv) (pdf)
Erfan Seyedsalehi, Nima Akbarzadeh, Amit Sinha, and Aditya Mahajan
European Workshop on Reinforcement Learning, Jun 2023.
Robustness and sample complexity of model-based MARL for general-sum Markov games (pdf)
Jayakumar Subramanian, Amit Sinha, and Aditya Mahajan
Dynamic Games and Application, pp. 56-88, Mar 2023.
DOI: 10.1007/s13235-023-00490-2
Robustness of Markov perfect equilibrium to model approximations in general-sum dynamic games (pdf)
Jayakumar Subramanian, Amit Sinha, and Aditya Mahajan
Indian Control Conference, Dec 2021.
An Approach Towards Automated Navigation of Vehicles using Overhead Cameras (pdf)
V. Sri Chakra Kumar, Amit Sinha, Pratheek P. Mallya, and Nutanlata Nath
IEEE International Conference on Computational Intelligence and Computing Research, Dec 2017.

Reinforcement learning in partially observable environments using approximate information state (pdf)
Amit Sinha
McGill University, Dec 2021.