Learning with good feature representations in bandits and in rl with a generative model T Lattimore, C Szepesvari, G Weisz
International conference on machine learning, 5662-5670, 2020
210 2020 Politex: Regret bounds for policy iteration using expert prediction Y Abbasi-Yadkori, P Bartlett, K Bhatia, N Lazic, C Szepesvari, G Weisz
International Conference on Machine Learning, 3692-3702, 2019
157 2019 Exponential lower bounds for planning in mdps with linearly-realizable optimal action-value functions G Weisz, P Amortila, C Szepesvári
Algorithmic Learning Theory, 1237-1264, 2021
102 2021 Sample efficient deep reinforcement learning for dialogue systems with large action spaces G Weisz, P Budzianowski, PH Su, M Gašić
IEEE/ACM Transactions on Audio, Speech, and Language Processing 26 (11 …, 2018
101 2018 LeapsAndBounds: A method for approximately optimal algorithm configuration G Weisz, A Gyorgy, C Szepesvári
International Conference on Machine Learning, 5257-5265, 2018
47 2018 Exploration-enhanced politex Y Abbasi-Yadkori, N Lazic, C Szepesvari, G Weisz
arXiv preprint arXiv:1908.10479, 2019
36 2019 CapsAndRuns: An improved method for approximately optimal algorithm configuration G Weisz, A Gyorgy, C Szepesvári
International Conference on Machine Learning, 6707-6715, 2019
28 2019 On query-efficient planning in mdps under linear realizability of the optimal state-value function G Weisz, P Amortila, B Janzer, Y Abbasi-Yadkori, N Jiang, C Szepesvári
Conference on Learning Theory, 4355-4385, 2021
25 2021 Tensorplan and the few actions lower bound for planning in mdps under linear realizability of optimal value functions G Weisz, C Szepesvári, A György
International Conference on Algorithmic Learning Theory, 1097-1137, 2022
15 2022 Confident Approximate Policy Iteration for Efficient Local Planning in G Weisz, A György, T Kozuno, C Szepesvári
Advances in Neural Information Processing Systems 35, 25547-25559, 2022
11 2022 Optimistic natural policy gradient: a simple efficient policy optimization framework for online rl Q Liu, G Weisz, A György, C Jin, C Szepesvári
Advances in Neural Information Processing Systems 36, 2024
8 2024 Inter-device data transfer based on barcodes J Chien, R Ian Orton, G Weisz, V Varma
US Patent 9,600,701, 2017
7 2017 Exponential hardness of reinforcement learning with linear function approximation S Liu, G Mahajan, D Kane, S Lovett, G Weisz, C Szepesvári
The Thirty Sixth Annual Conference on Learning Theory, 1588-1617, 2023
6 * 2023 ImpatientCapsAndRuns: Approximately optimal algorithm configuration from an infinite pool G Weisz, A György, WI Lin, D Graham, K Leyton-Brown, C Szepesvari, ...
Advances in Neural Information Processing Systems 33, 17478-17488, 2020
6 2020 Online RL in Linearly G Weisz, A György, C Szepesvári
Advances in Neural Information Processing Systems 36, 2024
4 2024 Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear V Tkachuk, G Weisz, C Szepesvári
arXiv preprint arXiv:2405.16809, 2024
2024 The Complexity of Reinforcement Learning with Linear Function Approximation G Weisz
UCL (Univesity College London), 2024
2024 P: Regret Bounds for Policy Iteration Using Expert Prediction Y Abbasi-Yadkori, PL Bartle, K Bhatia, N Lazić, C Szepesvári, G Weisz
