Aditya Mahajan

10
Documents

Publications

Publications

A Theoretical Justification for Asymmetric Actor-Critic Algorithms

Gaspard Lambrechts , Damien Ernst , Aditya Mahajan
International Conference on Machine Learning, Jul 2025, Vancouver (BC), Canada. ⟨10.48550/arXiv.2501.19116⟩
Communication dans un congrès hal-05320575 v1
Image document

A vector almost-supermartingale convergence theorem and its applications

Aditya Mahajan , Silviu-Iulian Niculescu , Mathukumalli Vidyasagar
63rd IEEE Conference on Decision and Control (CDC 2024), IEEE, Dec 2024, Milan, Italy. ⟨10.1109/cdc56724.2024.10886079⟩
Communication dans un congrès hal-04770089 v1
Image document

Agent-state based policies in POMDPs: Beyond belief-state MDPs

Amit Sinha , Aditya Mahajan
63rd IEEE Conference on Decision and Control (CDC 2024), Dec 2024, Milan, Italy. pp.6722-6735, ⟨10.1109/CDC56724.2024.10886046⟩
Communication dans un congrès hal-05217075 v1
Image document

Constant step-size stochastic approximation with delayed updates

Aditya Mahajan , Silviu-Iulian Niculescu , Mathukumalli Vidyasagar
63rd IEEE Conference on Decision and Control (CDC 2024), IEEE, Dec 2024, Milan, Italy. ⟨10.1109/cdc56724.2024.10886824⟩
Communication dans un congrès hal-04765003 v2
Image document

Fatigue and Task Load Dependent Decision Referrals for Joint Binary Classification in Human-Automation Teams

Raihan Seraj , Jerome Le Ny , Aditya Mahajan
IEEE Control Systems Letters, 2025, 9, pp.1315-1320. ⟨10.1109/LCSYS.2025.3581647⟩
Article dans une revue hal-05217069 v1

Best Linear Controllers for Decentralized Linear Quadratic Systems

Mohammad Afshari , Aditya Mahajan
Journal of Systems Science and Complexity, 2025, 38 (1), pp.210-237. ⟨10.1007/s11424-025-4505-9⟩
Article dans une revue hal-05217073 v1

Model Approximation in MDPs With Unbounded Per-Step Cost

Berk Bozkurt , Aditya Mahajan , Ashutosh Nayyar , Yi Ouyang
IEEE Transactions on Automatic Control, 2025, 70 (7), pp.4624-4639. ⟨10.1109/TAC.2025.3532181⟩
Article dans une revue hal-05217071 v1

Two families of indexable partially observable restless bandits and Whittle index computation

Nima Akbarzadeh , Aditya Mahajan
Performance Evaluation, 2024, 163, pp.102394. ⟨10.1016/j.peva.2023.102394⟩
Article dans une revue hal-04395242 v1

On learning Whittle index policy for restless bandits with scalable regret

Nima Akbarzadeh , Aditya Mahajan
IEEE Transactions on Control of Network Systems, 2023, pp.1-12. ⟨10.1109/TCNS.2023.3333402⟩
Article dans une revue hal-04395251 v1

Decentralized Linear Quadratic Systems With Major and Minor Agents and Non-Gaussian Noise

Mohammad Afshari , Aditya Mahajan
IEEE Transactions on Automatic Control, 2023, 68 (8), pp.4666-4681. ⟨10.1109/TAC.2022.3210049⟩
Article dans une revue hal-04395271 v1