Yonathan Efroni

76 papers A* 30A 1Journal 44Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Imbalanced Gradients in RL Post-Training of Multi-Task LLMs. EACL (Findings) Runzhe Wu, Ankur Samanta, Ayush Jain, Scott Fujimoto, Jeongyeol Kwon, Ben Kretzu, Youliang Yu, Kaveh Hassani, Boris Vidolov, Yonathan Efroni
2026	J	`jnl`	Structure Enables Effective Self-Localization of Errors in LLMs. CoRR Ankur Samanta, Akshayaa Magesh, Ayush Jain, Kavosh Asadi, Youliang Yu, Daniel Jiang, Boris Vidolov, Kaveh Hassani, Paul Sajda, Jalaj Bhandari, Yonathan Efroni
2025	A*	`conf`	Aligned Multi Objective Optimization. ICML Yonathan Efroni, Ben Kretzu, Daniel Jiang, Jalaj Bhandari, Zheqing Zhu, Karen Ullrich
2025	J	`jnl`	Aligned Multi Objective Optimization. CoRR Yonathan Efroni, Ben Kertzu, Daniel Jiang, Jalaj Bhandari, Zheqing Zhu, Karen Ullrich
2025	A*	`conf`	Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank. ICLR Wenhao Zhan, Scott Fujimoto, Zheqing Zhu, Jason D. Lee, Daniel Jiang, Yonathan Efroni
2025	J	`jnl`	Gradient Free Deep Reinforcement Learning With TabPFN. CoRR David Schiff, Ofir Lindenbaum, Yonathan Efroni
2025	J	`jnl`	Imbalanced Gradients in RL Post-Training of Multi-Task LLMs. CoRR Runzhe Wu, Ankur Samanta, Ayush Jain, Scott Fujimoto, Jeongyeol Kwon, Ben Kretzu, Youliang Yu, Kaveh Hassani, Boris Vidolov, Yonathan Efroni
2025	J	`jnl`	Internalizing Self-Consistency in Language Models: Multi-Agent Consensus Alignment. CoRR Ankur Samanta, Akshayaa Magesh, Youliang Yu, Runzhe Wu, Ayush Jain, Daniel Jiang, Boris Vidolov, Paul Sajda, Yonathan Efroni, Kaveh Hassani
2025	J	`jnl`	Simple Optimizers for Convex Aligned Multi-Objective Optimization. CoRR Ben Kretzu, Karen Ullrich, Yonathan Efroni
2025	A*	`conf`	Time After Time: Deep-Q Effect Estimation for Interventions on When and What to do. ICLR Yoav Wald, Mark Goldstein, Yonathan Efroni, Wouter A. C. van Amsterdam, Rajesh Ranganath
2025	J	`jnl`	Time After Time: Deep-Q Effect Estimation for Interventions on When and What to do. CoRR Yoav Wald, Mark Goldstein, Yonathan Efroni, Wouter A. C. van Amsterdam, Rajesh Ranganath
2024	J	`jnl`	Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank. CoRR Wenhao Zhan, Scott Fujimoto, Zheqing Zhu, Jason D. Lee, Daniel R. Jiang, Yonathan Efroni
2024	J	`jnl`	Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs. CoRR Lili Wu, Ben Evans, Riashat Islam, Raihan Seraj, Yonathan Efroni, Alex Lamb
2024	A*	`conf`	PcLast: Discovering Plannable Continuous Latent States. ICML Anurag Koul, Shivakanth Sujit, Shaoru Chen, Ben Evans, Lili Wu, Byron Xu, Rajan Chari, Riashat Islam, Raihan Seraj, Yonathan Efroni, Lekan P. Molu, Miroslav Dudík, John Langford, Alex Lamb
2024	J	`jnl`	Pearl: A Production-Ready Reinforcement Learning Agent. J. Mach. Learn. Res. Zheqing Zhu, Rodrigo de Salvo Braz, Jalaj Bhandari, Daniel Jiang, Yi Wan, Yonathan Efroni, Liyuan Wang, Ruiyang Xu, Hongbo Guo, Alex Nikulkov, Dmytro Korenkevych, Ürün Dogan, Frank Cheng, Zheng Wu, Wanqiao Xu
2024	A*	`conf`	Prospective Side Information for Latent MDPs. ICML Jeongyeol Kwon, Yonathan Efroni, Shie Mannor, Constantine Caramanis
2024	A*	`conf`	RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation. NeurIPS Jeongyeol Kwon, Shie Mannor, Constantine Caramanis, Yonathan Efroni
2024	J	`jnl`	RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation. CoRR Jeongyeol Kwon, Shie Mannor, Constantine Caramanis, Yonathan Efroni
2024	J	`jnl`	The Bias of Harmful Label Associations in Vision-Language Models. CoRR Caner Hazirbas, Alicia Sun, Yonathan Efroni, Mark Ibrahim
2023	J	`jnl`	Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models. Trans. Mach. Learn. Res. Alex Lamb, Riashat Islam, Yonathan Efroni, Aniket Rajiv Didolkar, Dipendra Misra, Dylan J. Foster, Lekan P. Molu, Rajan Chari, Akshay Krishnamurthy, John Langford
2023	J	`jnl`	PcLast: Discovering Plannable Continuous Latent States. CoRR Anurag Koul, Shivakanth Sujit, Shaoru Chen, Ben Evans, Lili Wu, Byron Xu, Rajan Chari, Riashat Islam, Raihan Seraj, Yonathan Efroni, Lekan P. Molu, Miro Dudík, John Langford, Alex Lamb
2023	J	`jnl`	Pearl: A Production-ready Reinforcement Learning Agent. CoRR Zheqing Zhu, Rodrigo de Salvo Braz, Jalaj Bhandari, Daniel Jiang, Yi Wan, Yonathan Efroni, Liyuan Wang, Ruiyang Xu, Hongbo Guo, Alex Nikulkov, Dmytro Korenkevych, Ürün Dogan, Frank Cheng, Zheng Wu, Wanqiao Xu
2023	A*	`conf`	Principled Offline RL in the Presence of Rich Exogenous Information. ICML Riashat Islam, Manan Tomar, Alex Lamb, Yonathan Efroni, Hongyu Zang, Aniket Rajiv Didolkar, Dipendra Misra, Xin Li, Harm van Seijen, Remi Tachet des Combes, John Langford
2023	J	`jnl`	Prospective Side Information for Latent MDPs. CoRR Jeongyeol Kwon, Yonathan Efroni, Shie Mannor, Constantine Caramanis
2023	A*	`conf`	Reward-Mixing MDPs with Few Latent Contexts are Learnable. ICML Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
2022	J	`jnl`	Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information. CoRR Riashat Islam, Manan Tomar, Alex Lamb, Yonathan Efroni, Hongyu Zang, Aniket Didolkar, Dipendra Misra, Xin Li, Harm van Seijen, Remi Tachet des Combes, John Langford
2022	A*	`conf`	Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms. ICML Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
2022	J	`jnl`	Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms. CoRR Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
2022	J	`jnl`	Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models. CoRR Alex Lamb, Riashat Islam, Yonathan Efroni, Aniket Didolkar, Dipendra Misra, Dylan J. Foster, Lekan P. Molu, Rajan Chari, Akshay Krishnamurthy, John Langford
2022	A*	`conf`	Mirror Descent Policy Optimization. ICLR Manan Tomar, Lior Shani, Yonathan Efroni, Mohammad Ghavamzadeh
2022	A*	`conf`	Provable Reinforcement Learning with a Short-Term Memory. ICML Yonathan Efroni, Chi Jin, Akshay Krishnamurthy, Sobhan Miryoosefi
2022	J	`jnl`	Provable Reinforcement Learning with a Short-Term Memory. CoRR Yonathan Efroni, Chi Jin, Akshay Krishnamurthy, Sobhan Miryoosefi
2022	A*	`conf`	Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics. ICLR Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford
2022	J	`jnl`	Reward-Mixing MDPs with a Few Latent Contexts are Learnable. CoRR Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
2022	A*	`conf`	Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information. COLT Yonathan Efroni, Dylan J. Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
2022	J	`jnl`	Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information. CoRR Yonathan Efroni, Dylan J. Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
2022	A*	`conf`	Sparsity in Partially Controllable Linear Systems. ICML Yonathan Efroni, Sham M. Kakade, Akshay Krishnamurthy, Cyril Zhang
2022	A*	`conf`	Tractable Optimality in Episodic Latent MABs. NeurIPS Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
2022	J	`jnl`	Tractable Optimality in Episodic Latent MABs. CoRR Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
2021	A	`conf`	Bandits with partially observable confounded data. UAI Guy Tennenholtz, Uri Shalit, Shie Mannor, Yonathan Efroni
2021	A*	`conf`	Confidence-Budget Matching for Sequential Budgeted Learning. ICML Yonathan Efroni, Nadav Merlis, Aadirupa Saha, Shie Mannor
2021	J	`jnl`	Confidence-Budget Matching for Sequential Budgeted Learning. CoRR Yonathan Efroni, Nadav Merlis, Aadirupa Saha, Shie Mannor
2021	J	`jnl`	Dare not to Ask: Problem-Dependent Guarantees for Budgeted Bandits. CoRR Nadav Merlis, Yonathan Efroni, Shie Mannor
2021	A*	`conf`	Minimax Regret for Stochastic Shortest Path. NeurIPS Alon Cohen, Yonathan Efroni, Yishay Mansour, Aviv Rosenberg
2021	J	`jnl`	Minimax Regret for Stochastic Shortest Path. CoRR Alon Cohen, Yonathan Efroni, Yishay Mansour, Aviv Rosenberg
2021	J	`jnl`	Provable RL with Exogenous Distractors via Multistep Inverse Dynamics. CoRR Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford
2021	A*	`conf`	RL for Latent MDPs: Regret Guarantees and a Lower Bound. NeurIPS Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
2021	J	`jnl`	RL for Latent MDPs: Regret Guarantees and a Lower Bound. CoRR Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
2021	A*	`conf`	Reinforcement Learning in Reward-Mixing MDPs. NeurIPS Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
2021	J	`jnl`	Reinforcement Learning in Reward-Mixing MDPs. CoRR Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
2021	A*	`conf`	Reinforcement Learning with Trajectory Feedback. AAAI Yonathan Efroni, Nadav Merlis, Shie Mannor
2021	J	`jnl`	Sparsity in Partially Controllable Linear Systems. CoRR Yonathan Efroni, Sham M. Kakade, Akshay Krishnamurthy, Cyril Zhang
2020	A*	`conf`	Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs. AAAI Lior Shani, Yonathan Efroni, Shie Mannor
2020	J	`jnl`	Bandits with Partially Observable Offline Data. CoRR Guy Tennenholtz, Uri Shalit, Shie Mannor, Yonathan Efroni
2020	J	`jnl`	Exploration-Exploitation in Constrained MDPs. CoRR Yonathan Efroni, Shie Mannor, Matteo Pirotta
2020	J	`jnl`	Mirror Descent Policy Optimization. CoRR Manan Tomar, Lior Shani, Yonathan Efroni, Mohammad Ghavamzadeh
2020	A*	`conf`	Multi-step Greedy Reinforcement Learning Algorithms. ICML Manan Tomar, Yonathan Efroni, Mohammad Ghavamzadeh
2020	A*	`conf`	Online Planning with Lookahead Policies. NeurIPS Yonathan Efroni, Mohammad Ghavamzadeh, Shie Mannor
2020	A*	`conf`	Optimistic Policy Optimization with Bandit Feedback. ICML Lior Shani, Yonathan Efroni, Aviv Rosenberg, Shie Mannor
2020	J	`jnl`	Optimistic Policy Optimization with Bandit Feedback. CoRR Yonathan Efroni, Lior Shani, Aviv Rosenberg, Shie Mannor
2020	J	`jnl`	Reinforcement Learning with Trajectory Feedback. CoRR Yonathan Efroni, Nadav Merlis, Shie Mannor
2019	A*	`conf`	Action Robust Reinforcement Learning and Applications in Continuous Control. ICML Chen Tessler, Yonathan Efroni, Shie Mannor
2019	J	`jnl`	Action Robust Reinforcement Learning and Applications in Continuous Control. CoRR Chen Tessler, Yonathan Efroni, Shie Mannor
2019	J	`jnl`	Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs. CoRR Lior Shani, Yonathan Efroni, Shie Mannor
2019	A*	`conf`	Exploration Conscious Reinforcement Learning Revisited. ICML Lior Shani, Yonathan Efroni, Shie Mannor
2019	A*	`conf`	How to Combine Tree-Search Methods in Reinforcement Learning. AAAI Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
2019	J	`jnl`	Multi-Step Greedy and Approximate Real Time Dynamic Programming. CoRR Yonathan Efroni, Mohammad Ghavamzadeh, Shie Mannor
2019	J	`jnl`	Multi-step Greedy Policies in Model-Free Deep Reinforcement Learning. CoRR Manan Tomar, Yonathan Efroni, Mohammad Ghavamzadeh
2019	A*	`conf`	Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies. NeurIPS Yonathan Efroni, Nadav Merlis, Mohammad Ghavamzadeh, Shie Mannor
2019	J	`jnl`	Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies. CoRR Yonathan Efroni, Nadav Merlis, Mohammad Ghavamzadeh, Shie Mannor
2018	J	`jnl`	Beyond the One Step Greedy Approach in Reinforcement Learning. CoRR Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
2018	A*	`conf`	Beyond the One-Step Greedy Approach in Reinforcement Learning. ICML Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
2018	J	`jnl`	How to Combine Tree-Search Methods in Reinforcement Learning. CoRR Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
2018	A*	`conf`	Multiple-Step Greedy Policies in Approximate and Online Reinforcement Learning. NeurIPS Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
2018	J	`jnl`	Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learning. CoRR Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
2018	J	`jnl`	Revisiting Exploration-Conscious Reinforcement Learning. CoRR Lior Shani, Yonathan Efroni, Shie Mannor