Gellért Weisz

25 papers A* 11B 2Journal 12

Year	Rank	Type	Title / Venue / Authors
2024	A*	`conf`	Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear q NeurIPS Volodymyr Tkachuk, Gellért Weisz, Csaba Szepesvári
2024	J	`jnl`	Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear q CoRR Volodymyr Tkachuk, Gellért Weisz, Csaba Szepesvári
2023	A*	`conf`	Exponential Hardness of Reinforcement Learning with Linear Function Approximation. COLT Sihan Liu, Gaurav Mahajan, Daniel Kane, Shachar Lovett, Gellért Weisz, Csaba Szepesvári
2023	J	`jnl`	Exponential Hardness of Reinforcement Learning with Linear Function Approximation. CoRR Daniel Kane, Sihan Liu, Shachar Lovett, Gaurav Mahajan, Csaba Szepesvári, Gellért Weisz
2023	A*	`conf`	Online RL in Linearly q NeurIPS Gellért Weisz, András György, Csaba Szepesvári
2023	J	`jnl`	Online RL in Linearly q CoRR Gellért Weisz, András György, Csaba Szepesvári
2023	A*	`conf`	Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL. NeurIPS Qinghua Liu, Gellért Weisz, András György, Chi Jin, Csaba Szepesvári
2023	J	`jnl`	Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL. CoRR Qinghua Liu, Gellért Weisz, András György, Chi Jin, Csaba Szepesvári
2022	A*	`conf`	Confident Approximate Policy Iteration for Efficient Local Planning in $q^\pi$-realizable MDPs. NeurIPS Gellért Weisz, András György, Tadashi Kozuno, Csaba Szepesvári
2022	J	`jnl`	Confident Approximate Policy Iteration for Efficient Local Planning in q CoRR Gellért Weisz, András György, Tadashi Kozuno, Csaba Szepesvári
2022	B	`conf`	TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions. ALT Gellért Weisz, Csaba Szepesvári, András György
2021	B	`conf`	Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions. ALT Gellért Weisz, Philip Amortila, Csaba Szepesvári
2021	A*	`conf`	On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function. COLT Gellért Weisz, Philip Amortila, Barnabás Janzer, Yasin Abbasi-Yadkori, Nan Jiang, Csaba Szepesvári
2021	J	`jnl`	On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function. CoRR Gellért Weisz, Philip Amortila, Barnabás Janzer, Yasin Abbasi-Yadkori, Nan Jiang, Csaba Szepesvári
2021	J	`jnl`	TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions. CoRR Gellért Weisz, Csaba Szepesvári, András György
2020	J	`jnl`	Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions. CoRR Gellért Weisz, Philip Amortila, Csaba Szepesvári
2020	A*	`conf`	ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool. NeurIPS Gellért Weisz, András György, Wei-I Lin, Devon R. Graham, Kevin Leyton-Brown, Csaba Szepesvári, Brendan Lucier
2020	A*	`conf`	Learning with Good Feature Representations in Bandits and in RL with a Generative Model. ICML Tor Lattimore, Csaba Szepesvári, Gellért Weisz
2019	A*	`conf`	CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration. ICML Gellért Weisz, András György, Csaba Szepesvári
2019	J	`jnl`	Exploration-Enhanced POLITEX. CoRR Yasin Abbasi-Yadkori, Nevena Lazic, Csaba Szepesvári, Gellért Weisz
2019	A*	`conf`	POLITEX: Regret Bounds for Policy Iteration using Expert Prediction. ICML Yasin Abbasi-Yadkori, Peter L. Bartlett, Kush Bhatia, Nevena Lazic, Csaba Szepesvári, Gellért Weisz
2018	A*	`conf`	LEAPSANDBOUNDS: A Method for Approximately Optimal Algorithm Configuration. ICML Gellért Weisz, András György, Csaba Szepesvári
2018	J	`jnl`	LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration. CoRR Gellért Weisz, András György, Csaba Szepesvári
2018	J	`jnl`	Sample Efficient Deep Reinforcement Learning for Dialogue Systems With Large Action Spaces. IEEE ACM Trans. Audio Speech Lang. Process. Gellért Weisz, Pawel Budzianowski, Pei-Hao Su, Milica Gasic
2018	J	`jnl`	Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces. CoRR Gellért Weisz, Pawel Budzianowski, Pei-Hao Su, Milica Gasic