Journal Publications

Preprints

42. Model approximation in MDPs with unbounded per-step cost (arxiv)
    Berk Bozkurt, Aditya Mahajan, Ashutosh Nayyar and Yi Ouyang
    Feb 2024.
41. Mean-field games among teams (arxiv)
    Jayakumar Subramanian, Akshat Kumar and Aditya Mahajan
    Oct 2023.
40. Approximate information state based convergence analysis of recurrent Q-learning (arxiv)
    Erfan Seyedsalehi, Nima Akbarzadeh, Amit Sinha and Aditya Mahajan
    June 2023.
39. On the sensitivity of restless bandit solutions to model mismatch (pdf)
    Amit Sinha and Aditya Mahajan
    March 2022.

Journal and Selective Conference Publications

38. Strong consistency and rate of convergence of switched least squares system identification for autonomous switched Markov jump linear systems (pdf)
    Borna Sayedana, Mohammad Afshari, Peter E. Caines and Aditya Mahajan
    July 2024 (in print).
    DOI: 10.1109/TAC.2024.3351806.
37. On learning Whittle index policy for restless bandits with scalable regret (pdf)
    Nima Akbarzadeh and Aditya Mahajan
    IEEE Transactions on Control of Networked Systems, July 2023 (accepted).
    DOI: 10.1109/TCNS.2023.3333402.
36. Briding State and History Representations: Understanding self-predictive RL (arxiv) (code)
    Tianwei Ni, Benjamin Eysenbach, Erfan SeyedSalehi, Michel Ma, Clement Gehring, Aditya Mahajan and Pierre-Luc Bacon
    International Confernece on Learning Representations (ICLR), May 2024.
35. On learning history-based policies for controlling Markov decision processes (arxiv)
    Gandharv Patil, Aditya Mahajan and Doina Precup
    International Conference on Artificial Intelligence and Statistics (AISTATS), May 2024.
34. Two families of indexable partially observable restless bandits and Whittle index computation (pdf)
    Nima Akbarzadeh and Aditya Mahajan
    Performance Evaluation, pp. 102394, Jan 2024.
    DOI: 10.1016/j.peva.2023.102394.
33. 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.
32. Decentralized linear quadratic systems with major and minor agents and non-Gaussian noise (pdf)
    Mohammad Afshari and Aditya Mahajan
    IEEE Transcations on Automatic Control, vol. 68, no. 8, pp. 4666–4681, Aug 2023.
    DOI: 10.1109/TAC.2022.3210049.
31. Scalable regret for learning to control network-coupled subsystems with unknown dynamics (pdf)
    Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar and Ouyang Yi
    IEEE Transactions on Control of Networked Systems, vol. 10, no. 1, pp. 2-14, March 2023.
    DOI: 10.1109/TCNS.2022.3184107.
30. 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, March 2023.
    DOI: 10.1007/s13235-023-00490-2.
29. Structure-aware reinforcement learning for node overload protection in mobile edge computing (pdf)
    Anirudha Jitani, Aditya Mahajan, Zhongwen Zhu, Hatem Abou-zeid, Emannuel T. Fapi and Hakimeh Purmehdi
    IEEE Transactions on Cognitive Communications and Networking, vol. 8, no. 4, pp. 1881-1897, Dec 2022.
    DOI: 10.1109/TCCN.2022.3195503.
28. Conditions for indexability of restless bandits and an O(K³) algorithm to compute Whittle index (pdf) (code)
    Nima Akbarzadeh and Aditya Mahajan
    Journal of Applied Probability, vol. 54, no. 4, pp. 1164-1192, Dec 2022.
    DOI: 10.1017/apr.2021.61.
27. Scalable operator allocation for multi-robot assistance: A restless bandit approach (pdf) (code)
    Abhinav Dahiya, Nima Akbarzadeh, Aditya Mahajan and Stephen L. Smith
    IEEE Transactions on Control of Networked Systems, vol. 9, no. 3, pp. 1397-1408, Sep 2022.
    DOI: 10.1109/TCNS.2022.3153872.
26. Optimal control of network-coupled subsystems: Spectral decomposition and low-dimensional solutions (pdf)
    Shuang Gao and Aditya Mahajan
    IEEE Transactions on Control of Networked Systems, vol. 9, no. 2, pp. 657-669, June 2022.
    DOI: 10.1109/TCNS.2021.3124259.
25. 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.
24. Multi-agent estimation and filtering for minimizing team mean-squared error (pdf)
    Mohammad Afshari and Aditya Mahajan
    IEEE Transactions on Signal Processing, vol. 69, pp. 5206-5221, Aug 2021.
    DOI: 10.1109/TSP.2021.3104981.
23. Optimal local and remote controllers with unreliable uplink channels: An elementary proof (pdf)
    Mohammad Afshari and Aditya Mahajan
    IEEE Transcations on Automatic Control, vol. 65, no. 8, pp. 3616–3622, Aug 2020.
    DOI: 10.1109/TAC.2019.2951658.
22. Renewal Monte Carlo: Renewal theory based reinforcement learning (pdf) (code)
    Jayakumar Subramanian and Aditya Mahajan
    IEEE Transcations on Automatic Control, vol. 65, no. 8, pp. 3663–3670, Aug 2020.
    DOI: 10.1109/TAC.2019.2953089.
21. Counterexamples on the monotonicity of delay optimal strategies for energy harvesting transmitters (pdf) (code)
    Borna Sayedana and Aditya Mahajan
    IEEE Wireless Communication Letters, vol. 9, no. 7, pp. 1070-1074, July 2020.
    DOI: 10.1109/LWC.2020.2981066.
20. Remote estimation over a packet-drop channel with Markovian state (pdf) (code)
    Jhelum Chakravorty and Aditya Mahajan
    IEEE Transcations on Automatic Control, vol. 65, no. 5, pp. 2016-2031, May 2020.
    DOI: 10.1109/TAC.2019.2926160.
19. Reinforcement learning in stationary mean-field games (pdf)
    Jayakumar Subramanian and Aditya Mahajan
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2019.
    ACMID: 3331700.
18. Sufficient conditions for the value function and optimal strategy to be even and quasi-convex (pdf) (code)
    Jhelum Chakravorty and Aditya Mahajan
    IEEE Transcations on Automatic Control, vol. 63, no. 11, Nov 2018.
    DOI: 10.1109/TAC.2018.2800796.
17. Information-Theoretic Privacy for Smart Metering Systems with a Rechargeable Battery (pdf)
    Simon Li, Ashish Khisti and Aditya Mahajan
    IEEE Transcations on Information Theory, vol. 64, no. 5, pp. 3679–3695, May 2018.
    DOI: 10.1109/TIT.2018.2809005.
16. Fundamental limits of remote estimation of autoregressive Markov processes under communication constraints (pdf)
    Jhelum Chakravorty and Aditya Mahajan
    IEEE Transactions on Automatic Control, March 2017.
    DOI: 10.1109/TAC.2016.2580589.
15. Decentralized stochastic control (pdf)
    Aditya Mahajan and Mehnaz Mannan
    Annals of Operations Research, vol. 241, no. 1, pp. 109–126, June 2016.
    DOI: 10.1007/s10479-014-1652-0.
14. An algorithmic approach to identify irrelevant information in sequential teams (pdf)
    Aditya Mahajan and Sekhar Tatikonda
    Automatica, pp. 178–191, Nov 2015.
    DOI: 10.1016/j.automatica.2015.08.002.
13. Sufficient statistics for linear control strategies in decentralized systems with partial history sharing (pdf)
    Aditya Mahajan and Ashutosh Nayyar
    IEEE Transactions on Automatic Control, vol. 60, no. 8, pp. 2046–2056, Aug 2015.
    DOI: 10.1109/TAC.2015.2398884.
12. Optimal decentralized control of coupled subsystems with control sharing (pdf)
    Aditya Mahajan
    IEEE Transactions on Automatic Control, vol. 58, no. 9, pp. 2377-2382, Sep 2013.
    DOI: 10.1109/TAC.2013.2251807.
11. Decentralized stochastic control with partial history sharing: A common information approach (pdf)
    Ashutosh Nayyar, Aditya Mahajan and Demosthenis Teneketzis
    IEEE Transactions on Automatic Control, vol. 58, no. 7, pp. 1644-1658, July 2013.
    DOI: 10.1109/TAC.2013.2239000.
    Recipient of the 2015 George Axelby Outstanding Paper Award.
10. Information structures in optimal decentralized control (pdf)
    Aditya Mahajan, Nuno C. Martins, Michael C. Rotkowitz and Serdar Yüksel
    IEEE Conference on Decision and Control (CDC), pp. 1291–1306, Dec 2012.
    DOI: 10.1109/CDC.2012.6425819.
9. Opportunistic capacity and error exponent region for the compound channel with feedback (pdf) (code)
   Aditya Mahajan and Sekhar Tatikonda
   IEEE Transactions on Information Theory, vol. 58, no. 7, pp. 4331-4341, July 2012.
   DOI: 10.1109/TIT.2012.2191689.
8. Optimal control strategies in delayed sharing information structures (pdf)
   Ashutosh Nayyar, Aditya Mahajan and Demosthenis Teneketzis
   IEEE Transactions on Automatic Control, vol. 56, no. 7, pp. 1606-1620, July 2011.
   DOI: 10.1109/TAC.2010.2089381.
7. A wireless soil moisture smart sensor web using physics-based optimal control: Concept and initial demonstrations (pdf)
   Mahta Moghaddam, Dara Entekhabi, Yuriy Goykhman, Ke Li, Mingyan Liu, Aditya Mahajan, Ashutosh Nayyar, David I Shuman and Demosthenis Teneketzis
   IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 3, no. 4, pp. 522-535, Dec 2010.
   DOI: 10.1109/JSTARS.2010.2052918.
6. Measurement scheduling for soil moisture sensing: From physical models to optimal control (pdf)
   David Shuman, Ashutosh Nayyar, Aditya Mahajan, Yuriy Goykhman, Ke Li, Mingyan Liu, Demosthenis Teneketzis, Mahta Moghaddam and Dara Entekhabi
   Proceedings of the IEEE, special issue on Sensor Networks and Applications, vol. 98, no. 11, pp. 1918-1934, Nov 2010.
   DOI: 10.1109/JPROC.2010.2052532.
5. Optimal design of sequential real-time communication systems (pdf) (code)
   Aditya Mahajan and Demosthenis Teneketzis
   IEEE Transactions on Information Theory, vol. 55, no. 11, pp. 5317-5337, Nov 2009.
   DOI: 10.1109/TIT.2009.2030462.
4. Optimal performance of networked control systems with non-classical information structures (pdf)
   Aditya Mahajan and Demosthenis Teneketzis
   SIAM Journal of Control and Optimization, vol. 48, no. 3, pp. 1377-1404, May 2009.
   DOI: 10.1137/060678130.
3. On the design of globally optimal communication strategies for real-time noisy communication with noisy feedback (pdf)
   Aditya Mahajan and Demosthenis Teneketzis
   IEEE Journal on Selected Areas in Communication, vol. 28, no. 4, pp. 580-595, May 2008.
   DOI: 10.1109/JSAC.2008.080502.
2. A novel method of down conversion for multiple bandpass signals (pdf)
   Aditya Mahajan, Manu Agarwal and Ajit K. Chaturvedi
   IEEE Transactions on Wireless Communication, vol. 5, no. 2, pp. 427-434, Feb 2006.
   DOI: 10.1109/TWC.2006.1611066.
1. An improved interpretation of depletion approximation in p-n junctions (pdf)
   Baquer Mazhari and Aditya Mahajan
   IEEE Transactions on Education, vol. 48, no. 1, pp. 60-62, Feb 2005.
   DOI: 10.1109/TE.2004.832876.

Book Chapters

3. Multi-armed bandits, Gittins index, and its calculation (pdf)
   Jhelum Chakravorty, and Aditya Mahajan
   Methods and Applications of Statistics in Clinical Trials, Volume 2: Planning, Analysis, and Inferential Methods, pp. 416-435, John Wiley & Sons, 2014.
   DOI: 10.1002/9781118596333.ch24.
2. The common-information approach to decentralized stochastic control (pdf)
   Ashutosh Nayyar, Aditya Mahajan, and Demosthenis Teneketzis
   Information and Control in Networks, pp. 123-156, Springer-Verlag, 2014.
   DOI: 10.1007/978-3-319-02150-8_4.
1. Multi-armed bandit problems (pdf)
   Aditya Mahajan, and Demosthenis Teneketzis
   Foundations and Applications of Sensor Management, pp. 121-151, Springer-Verlag, 2008.
   DOI: 10.1007/978-0-387-49819-5_6.

Thesis

• Sequential decomposition of sequential teams: applications to real-time communication and networked control systems (pdf)
  Aditya Mahajan
  University of Michigan, September 2008. Supervised by Demos Teneketzis.

Unpublished drafts

• Linear Quadratic Mean Field Teams: Optimal and Approximately Optimal Decentralized Solutions (pdf)
  Jalal Arabneydi and Aditya Mahajan
  Aug 2016.
• On computing optimal thresholds in decentralized sequential hypothesis testing (pdf)
  Can Cui and Aditya Mahajan
  Jan 2016.
• Question about measurability of optimal control strategies in static teams (pdf)
  Aditya Mahajan, Ashutosh Nayyar and Demosthenis Teneketzis
  Oct 2015.
• On the relationship between maximin information and common knowledge (pdf)
  Aditya Mahajan
  Jan 2014.
• Structural results for MDP: A direct proof (pdf)
  Aditya Mahajan
  Jun 2010.

Disclaimer

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All person copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.