DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning, A Bura, A HasanzadeZonuzy, D Kalathil, S Shakkottai, Jean-Francois Chamberland, accepted to NeurIPS 2022.
arXiv preprint arXiv:2112.00885, [arxiv]
Learning with Safety Constraints: Sample Complexity of Reinforcement Learning for Constrained MDPs, A HasanzadeZonuzy, A Bura, D Kalathil, S Shakkottai, [AAAI]
Learning to Cache and Caching to Learn: Regret Analysis of Caching Algorithms, Archana Bura, Desik Rengarajan, Dileep Kalathil, Srinivas Shakkottai, Jean-Francois Chamberland-Tremblay, IEEE Transactions on Networking, 2021 [ToN]
Qflow: A reinforcement learning approach to high qoe video streaming over wireless networks, Rajarshi Bhattacharyya, Archana Bura, Desik Rengarajan, Mason Rumuly, Srinivas Shakkottai, Dileep Kalathil, Ricky KP Mok, Amogh Dhamdhere, Mobihoc '19: Proceedings of the Twentieth ACM International Symposium on Mobile Ad Hoc Networking and ComputingJuly 2019. [MobiHoc]
Qflow: A learning approach to high qoe video streaming at the wireless edge, Rajarshi Bhattacharyya, Archana Bura, Desik Rengarajan, Mason Rumuly, Bainan Xia, Srinivas Shakkottai, Dileep Kalathil, Ricky KP Mok, Amogh Dhamdhere, IEEE/ACM Transactions on Networking, 2021. [ToN]
Latency analysis for distributed storage, Parimal Parag, Archana Bura, Jean-Francois Chamberland, IEEE INFOCOM 2017-IEEE Conference on Computer Communications. [INFOCOM]
Throughput of TCP over Cognitive Radio Channels, Sudheer Poojary, Akash Agrawal, Bhoomika Gupta, Archana Bura, Vinod Sharma, 2015 IEEE Global Communications Conference (GLOBECOM). [GLOBECOM]