Gellért Weisz

Publication Activity (10 Years)

Years Active: 2018-2023
Publications (10 Years): 22

Top Topics

Markov Decision Problems

Feature Representations

Reinforcement Learning

Top Venues

Publications

Qinghua Liu, Gellért Weisz, András György, Chi Jin, Csaba Szepesvári
Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL. CoRR (2023)
Gellért Weisz, András György, Csaba Szepesvári
-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore. CoRR (2023)
Daniel Kane, Sihan Liu, Shachar Lovett, Gaurav Mahajan, Csaba Szepesvári, Gellért Weisz
Exponential Hardness of Reinforcement Learning with Linear Function Approximation. CoRR (2023)
Gellért Weisz, András György, Csaba Szepesvári
-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore. NeurIPS (2023)
Qinghua Liu, Gellért Weisz, András György, Chi Jin, Csaba Szepesvári
Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL. NeurIPS (2023)
Sihan Liu, Gaurav Mahajan, Daniel Kane, Shachar Lovett, Gellért Weisz, Csaba Szepesvári
Exponential Hardness of Reinforcement Learning with Linear Function Approximation. COLT (2023)
Gellért Weisz, Csaba Szepesvári, András György
TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions. ALT (2022)
Gellért Weisz, András György, Tadashi Kozuno, Csaba Szepesvári
-realizable MDPs. CoRR (2022)
Gellért Weisz, András György, Tadashi Kozuno, Csaba Szepesvári
Confident Approximate Policy Iteration for Efficient Local Planning in $q^\pi$-realizable MDPs. NeurIPS (2022)
Gellért Weisz, Philip Amortila, Csaba Szepesvári
Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions. ALT (2021)
Gellért Weisz, Philip Amortila, Barnabás Janzer, Yasin Abbasi-Yadkori, Nan Jiang, Csaba Szepesvári
On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function. COLT (2021)
Gellért Weisz, Philip Amortila, Barnabás Janzer, Yasin Abbasi-Yadkori, Nan Jiang, Csaba Szepesvári
On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function. CoRR (2021)
Gellért Weisz, Csaba Szepesvári, András György
TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions. CoRR (2021)
Gellért Weisz, András György, Wei-I Lin, Devon R. Graham, Kevin Leyton-Brown, Csaba Szepesvári, Brendan Lucier
ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool. NeurIPS (2020)
Gellért Weisz, Philip Amortila, Csaba Szepesvári
Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions. CoRR (2020)
Tor Lattimore, Csaba Szepesvári, Gellért Weisz
Learning with Good Feature Representations in Bandits and in RL with a Generative Model. ICML (2020)
Gellért Weisz, András György, Csaba Szepesvári
CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration. ICML (2019)
Yasin Abbasi-Yadkori, Nevena Lazic, Csaba Szepesvári, Gellért Weisz
Exploration-Enhanced POLITEX. CoRR (2019)
Gellért Weisz, András György, Csaba Szepesvári
LEAPSANDBOUNDS: A Method for Approximately Optimal Algorithm Configuration. ICML (2018)
Gellért Weisz, Pawel Budzianowski, Pei-Hao Su, Milica Gasic
Sample Efficient Deep Reinforcement Learning for Dialogue Systems With Large Action Spaces. IEEE ACM Trans. Audio Speech Lang. Process. 26 (11) (2018)
Gellért Weisz, András György, Csaba Szepesvári
LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration. CoRR (2018)
Gellért Weisz, Pawel Budzianowski, Pei-Hao Su, Milica Gasic
Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces. CoRR (2018)