Amit Sinha

Retour

Publications

Cahiers du GERAD

nov. 2023

G-2023-57
Asymmetric actor-critic with approximate information state

Amit Sinha et Aditya Mahajan

L'apprentissage par renforcement (RL) pour les processus décisionnels de Markov partiellement observables (POMDP) est un problème difficile car les décisions...

référence BibTeX

Articles

mars 2023

Robustness and Sample Complexity of Model-Based MARL for General-Sum Markov Games

Jayakumar Subramanian, Amit Sinha et Aditya Mahajan

Dynamic Games and Applications, 13, 56–88, 2023 référence BibTeX

fév. 2022

Approximate Information State for Approximate Planning and Reinforcement Learning in Partially Observed Systems

Jayakumar Subramanian, Amit Sinha, Raihan Seraj et Aditya Mahajan

Journal of Machine Learning Research, 23(12), 1–83, 2022 référence BibTeX

Actes de conférence

déc. 2023

Asymmetric Actor-Critic with Approximate Information State

Amit Sinha et Aditya Mahajan

2023 62nd IEEE Conference on Decision and Control (CDC), Singapore, 7810–7816, 2023 référence BibTeX

août 2023

Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning

Hadi Nekoei, Akilesh Badrinaaraayanan, Amit Sinha, Mohammad Amini, Janarthanan Rajendran, Aditya Mahajan et Sarath Chandar

Conference on Lifelong Learning Agents, Montréal, Canada, 2023 référence BibTeX

déc. 2021

Robustness of Markov perfect equilibrium to model approximations in general-sum dynamic games

Jayakumar Subramanian, Amit Sinha et Aditya Mahajan

2021 Seventh Indian Control Conference (ICC), Mumbai, India, 2021 référence BibTeX