| Melting Pot 2.0 JP Agapiou, AS Vezhnevets, EA Duéñez-Guzmán, J Matyas, Y Mao, ... arXiv preprint arXiv:2211.13746, 2022 | 41 | 2022 |
| One more step towards reality: Cooperative bandits with imperfect communication U Madhushani, A Dubey, N Leonard, A Pentland Advances in Neural Information Processing Systems 34, 7813-7824, 2021 | 26 | 2021 |
| Semi-globally exponential trajectory tracking for a class of spherical robots TWU Madhushani, DHS Maithripala, JV Wijayakulasooriya, JM Berg Automatica 85, 327-338, 2017 | 26 | 2017 |
| Feedback regularization and geometric PID control for trajectory tracking of mechanical systems: Hoop robots on an inclined plane TWU Madhushani, DHS Maithripala, JM Berg 2017 American Control Conference (ACC), 3938-3943, 2017 | 24* | 2017 |
| A dynamic observation strategy for multi-agent multi-armed bandit problem U Madhushani, NE Leonard 2020 European control conference (ECC), 1677-1682, 2020 | 23 | 2020 |
| Multi-robot Learning and Coverage of Unknown Spatial Fields M Santos, U Madhushani, A Benevento, NE Leonard | 22 | 2021 |
| Heterogeneous stochastic interactions for multiple agents in a multi-armed bandit problem U Madhushani, NE Leonard 2019 18th European Control Conference (ECC), 3502-3507, 2019 | 22 | 2019 |
| Heterogeneous explore-exploit strategies on multi-star networks U Madhushani, NE Leonard 2021 American Control Conference (ACC), 1192-1197, 2021 | 21 | 2021 |
| Sorry-bench: Systematically evaluating large language model safety refusal behaviors T Xie, X Qi, Y Zeng, Y Huang, UM Sehwag, K Huang, L He, B Wei, D Li, ... arXiv preprint arXiv:2406.14598, 2024 | 14 | 2024 |
| Distributed learning: Sequential decision making in resource-constrained environments U Madhushani, NE Leonard arXiv preprint arXiv:2004.06171, 2020 | 12 | 2020 |
| Intrinsic PID controller for a segway type mobile robot ID Basnayake, TWU Madhushani, DHS Maithripala 2017 ieee international conference on industrial and information systems …, 2017 | 12 | 2017 |
| When to call your neighbor? strategic communication in cooperative stochastic bandits U Madhushani, N Leonard arXiv preprint arXiv:2110.04396, 2021 | 10 | 2021 |
| AI Risk Management Should Incorporate Both Safety and Security X Qi, Y Huang, Y Zeng, E Debenedetti, J Geiping, L He, K Huang, ... arXiv preprint arXiv:2405.19524, 2024 | 9 | 2024 |
| Provably efficient multi-agent reinforcement learning with fully decentralized communication J Lidard, U Madhushani, NE Leonard 2022 American Control Conference (ACC), 3311-3316, 2022 | 7 | 2022 |
| Heterogeneous social value orientation leads to meaningful diversity in sequential social dilemmas U Madhushani, KR McKee, JP Agapiou, JZ Leibo, R Everett, T Anthony, ... arXiv preprint arXiv:2305.00768, 2023 | 6 | 2023 |
| Distributed bandits: Probabilistic communication on d-regular graphs U Madhushani, NE Leonard 2021 European Control Conference (ECC), 830-835, 2021 | 6 | 2021 |
| A geometric pid control framework for mechanical systems DHS Maithripala, TWU Madhushani, JM Berg arXiv preprint arXiv:1610.04395, 2016 | 6 | 2016 |
| A Regret Minimization Approach to Multi-Agent Control U Ghai, U Madhushani, N Leonard, E Hazan arXiv preprint arXiv:2201.13288, 2022 | 5 | 2022 |
| It doesn’t get better and here’s why: A fundamental drawback in natural extensions of ucb to multi-agent bandits U Madhushani, N Leonard ''I Can't Believe It's Not Better!''NeurIPS 2020 workshop, 2020 | 5 | 2020 |
| A Heterogeneous Agent Model of Mortgage Servicing: An Income-based Relief Analysis D Garg, BP Evans, L Ardon, AL Narayanan, J Vann, U Madhushani, ... AAAI 2024 Workshop on AI in Finance for Social Impact, 2024 | 2 | 2024 |
Naomi LeonardProfessor of Mechanical and Aerospace Engineering, Princeton UniversityVerified email at princeton.edu
