{"list":"other","total":73,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"2310.01377","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","created":"2023-10-02","cited_by_count":406},{"id":"1901.11275","title":"A Theory of Regularized Markov Decision Processes","created":"2019-01-31","cited_by_count":286},{"id":"1711.00141","title":"Training GANs with Optimism","created":"2017-10-31","cited_by_count":217},{"id":"2002.04926","title":"Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles","created":"2020-02-12","cited_by_count":197},{"id":"1311.1869","title":"Optimization, Learning, and Games with Predictable Sequences","created":"2013-11-08","cited_by_count":188},{"id":"1705.07798","title":"A unified view of entropy-regularized Markov decision processes","created":"2017-05-22","cited_by_count":182},{"id":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174},{"id":"1507.00407","title":"Fast Convergence of Regularized Learning in Games","created":"2015-07-02","cited_by_count":150},{"id":"2407.01082","title":"Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs","created":"2024-07-01","cited_by_count":150},{"id":"1807.07623","title":"Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits","created":"2018-07-19","cited_by_count":124},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120},{"id":"2002.07530","title":"Improved Optimistic Algorithms for Logistic Bandits","created":"2020-02-18","cited_by_count":118},{"id":"1406.1853","title":"Model-based Reinforcement Learning and the Eluder Dimension","created":"2014-06-07","cited_by_count":116},{"id":"2002.04017","title":"Provable Self-Play Algorithms for Competitive Reinforcement Learning","created":"2020-02-10","cited_by_count":113},{"id":"2006.12007","title":"Near-Optimal Reinforcement Learning with Self-Play","created":"2020-06-22","cited_by_count":109},{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106},{"id":"2010.01604","title":"A Sharp Analysis of Model-based Reinforcement Learning with Self-Play","created":"2020-10-04","cited_by_count":105},{"id":"1807.11398","title":"Preference-based Online Learning with Dueling Bandits: A Survey","created":"2018-07-30","cited_by_count":102},{"id":"1502.06362","title":"Contextual Dueling Bandits","created":"2015-02-23","cited_by_count":101},{"id":"1901.08106","title":"Open-ended Learning in Symmetric Zero-sum Games","created":"2019-01-23","cited_by_count":96},{"id":"1704.09011","title":"Mostly Exploration-Free Algorithms for Contextual Bandits","created":"2017-04-28","cited_by_count":85},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83},{"id":"2010.03104","title":"Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective","created":"2020-10-07","cited_by_count":78},{"id":"2407.13399","title":"Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization","created":"2024-07-18","cited_by_count":78},{"id":"1803.06971","title":"What Doubling Tricks Can and Can't Do for Multi-Armed Bandits","created":"2018-03-19","cited_by_count":71},{"id":"2110.00871","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","created":"2021-10-02","cited_by_count":66},{"id":"2007.03285","title":"Stochastic Linear Bandits Robust to Adversarial Attacks","created":"2020-07-07","cited_by_count":65},{"id":"2105.15186","title":"Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization","created":"2021-05-31","cited_by_count":63},{"id":"2011.04020","title":"High-Dimensional Sparse Linear Bandits","created":"2020-11-08","cited_by_count":61},{"id":"2010.12642","title":"Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits","created":"2020-10-23","cited_by_count":57},{"id":"1907.11362","title":"Doubly-Robust Lasso Bandit","created":"2019-07-26","cited_by_count":49},{"id":"2006.02948","title":"Low-Rank Generalized Linear Bandit Problems","created":"2020-06-04","cited_by_count":49},{"id":"2106.03352","title":"The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces","created":"2021-06-07","cited_by_count":48},{"id":"1512.04152","title":"Fighting Bandits with a New Kind of Smoothness","created":"2015-12-14","cited_by_count":47},{"id":"2007.08477","title":"Sparsity-Agnostic Lasso Bandit","created":"2020-07-16","cited_by_count":44},{"id":"2111.12306","title":"Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability","created":"2021-11-24","cited_by_count":44},{"id":"1709.06293","title":"Sparse Markov Decision Processes with Causal Sparse Tsallis Entropy Regularization for Reinforcement Learning","created":"2017-09-19","cited_by_count":37},{"id":"2012.05862","title":"Understanding Learned Reward Functions","created":"2020-12-10","cited_by_count":37},{"id":"2202.04593","title":"Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models","created":"2022-02-09","cited_by_count":37},{"id":"2010.14563","title":"Adversarial Dueling Bandits","created":"2020-10-27","cited_by_count":33},{"id":"1601.03855","title":"A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits","created":"2016-01-15","cited_by_count":31},{"id":"2011.00819","title":"Self-Concordant Analysis of Generalized Linear Bandits with Forgetting","created":"2020-11-02","cited_by_count":29},{"id":"2407.13977","title":"A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits","created":"2024-07-19","cited_by_count":29},{"id":"2310.18554","title":"Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion","created":"2023-10-28","cited_by_count":24},{"id":"1802.03501","title":"Path Consistency Learning in Tsallis Entropy Regularized MDPs","created":"2018-02-10","cited_by_count":22},{"id":"2102.09626","title":"A Simple Unified Framework for High Dimensional Bandit Problems","created":"2021-02-18","cited_by_count":21},{"id":"2401.07298","title":"Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problems","created":"2024-01-14","cited_by_count":20},{"id":"2104.06970","title":"Understanding the Eluder Dimension","created":"2021-04-14","cited_by_count":19},{"id":"2410.21662","title":"$f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization","created":"2024-10-29","cited_by_count":19},{"id":"2107.09912","title":"Design of Experiments for Stochastic Contextual Linear Bandits","created":"2021-07-21","cited_by_count":18},{"id":"2210.15345","title":"PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits","created":"2022-10-25","cited_by_count":17},{"id":"2303.08816","title":"Borda Regret Minimization for Generalized Linear Dueling Bandits","created":"2023-03-15","cited_by_count":17},{"id":"2003.02681","title":"Stochastic Linear Contextual Bandits with Diverse Contexts","created":"2020-03-05","cited_by_count":16},{"id":"2006.05145","title":"Matrix games with bandit feedback","created":"2020-06-09","cited_by_count":16},{"id":"2210.01907","title":"A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games","created":"2022-10-04","cited_by_count":16},{"id":"2507.11847","title":"Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update","created":"2025-07-16","cited_by_count":16},{"id":"2510.01218","title":"Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs","created":"2025-09-20","cited_by_count":15},{"id":"2510.13060","title":"Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games","created":"2025-10-15","cited_by_count":15},{"id":"1710.08083","title":"Generalized High-Dimensional Trace Regression via Nuclear Norm Regularization","created":"2017-10-23","cited_by_count":12},{"id":"2312.15433","title":"Best-of-Both-Worlds Algorithms for Linear Contextual Bandits","created":"2023-12-24","cited_by_count":11},{"id":"2402.11156","title":"Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits","created":"2024-02-17","cited_by_count":10},{"id":"2405.16388","title":"Multi-Reference Preference Optimization for Large Language Models","created":"2024-05-26","cited_by_count":10},{"id":"2502.17625","title":"Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback","created":"2025-02-24","cited_by_count":10},{"id":"2510.04088","title":"Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees","created":"2025-10-05","cited_by_count":10},{"id":"2411.12878","title":"Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit","created":"2024-11-19","cited_by_count":8},{"id":"2003.06495","title":"Human Preference-Based Learning for High-dimensional Optimization of Exoskeleton Walking Gaits","created":"2020-03-13","cited_by_count":7},{"id":"2403.03219","title":"LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits","created":"2024-03-05","cited_by_count":4},{"id":"2506.03074","title":"GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression","created":"2025-06-03","cited_by_count":4},{"id":"2502.09780","title":"Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games","created":"2025-02-13","cited_by_count":3}],"next_cursor":null}