On the properties of the softmax function with application in game theory and reinforcement learning B Gao, L Pavel arXiv preprint arXiv:1704.00805, 2017 | 378 | 2017 |
On passivity, reinforcement learning, and higher order learning in multiagent finite games B Gao, L Pavel IEEE Transactions on Automatic Control 66 (1), 121-136, 2020 | 42 | 2020 |
Continuous-time discounted mirror descent dynamics in monotone concave games B Gao, L Pavel IEEE Transactions on Automatic Control 66 (11), 5451-5458, 2020 | 25 | 2020 |
Bandit learning with regularized second-order mirror descent B Gao, L Pavel 2022 IEEE 61st Conference on Decision and Control (CDC), 5731-5738, 2022 | 12 | 2022 |
On passivity and reinforcement learning in finite games B Gao, L Pavel 2018 IEEE Conference on Decision and Control (CDC), 340-345, 2018 | 9 | 2018 |
Continuous-time convergence rates in potential and monotone games B Gao, L Pavel SIAM Journal on Control and Optimization 60 (3), 1712-1731, 2022 | 7 | 2022 |
Discounted mirror descent dynamics in concave games B Gao, L Pavel 2019 IEEE 58th Conference on Decision and Control (CDC), 5942-5947, 2019 | 7 | 2019 |
Second-order mirror descent: Convergence in games beyond averaging and discounting B Gao, L Pavel IEEE Transactions on Automatic Control, 2023 | 3 | 2023 |
Second-order mirror descent: exact convergence beyond strictly stable equilibria in concave games B Gao, L Pavel 2021 60th IEEE Conference on Decision and Control (CDC), 948-953, 2021 | 3 | 2021 |
On the rate of convergence of continuous-time game dynamics in N-player potential games B Gao, L Pavel 2020 59th IEEE Conference on Decision and Control (CDC), 1678-1683, 2020 | 3 | 2020 |
Agent, Equilibrium and Learning: A Quest Towards Taming the Master Dynamics of Games B Gao University of Toronto (Canada), 2022 | | 2022 |
Higher-Order Game Dynamics in Population Games and Reinforcement Learning B Gao University of Toronto (Canada), 2017 | | 2017 |