{"list":"other","total":51,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"1912.13213","title":"Online Learning: A Modern Introduction Using Convex Optimization","created":"2019-12-31","cited_by_count":417},{"id":"2403.00409","title":"Provably Robust DPO: Aligning Language Models with Noisy Feedback","created":"2024-03-01","cited_by_count":135},{"id":"2002.07530","title":"Improved Optimistic Algorithms for Logistic Bandits","created":"2020-02-18","cited_by_count":118},{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106},{"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":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","cited_by_count":81},{"id":"2006.08910","title":"Preference-based Reinforcement Learning with Finite-Time Guarantees","created":"2020-06-16","cited_by_count":65},{"id":"2402.08114","title":"Active Preference Learning for Large Language Models","created":"2024-02-12","cited_by_count":58},{"id":"2010.12642","title":"Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits","created":"2020-10-23","cited_by_count":57},{"id":"1908.01289","title":"Dueling Posterior Sampling for Preference-Based Reinforcement Learning","created":"2019-08-04","cited_by_count":56},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53},{"id":"1506.02550","title":"Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem","created":"2015-06-08","cited_by_count":52},{"id":"1706.03880","title":"MNL-Bandit: A Dynamic Learning Approach to Assortment Selection","created":"2017-06-13","cited_by_count":50},{"id":"2201.11206","title":"Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes","created":"2022-01-26","cited_by_count":49},{"id":"2111.03289","title":"Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs","created":"2021-11-05","cited_by_count":44},{"id":"1604.07101","title":"Double Thompson Sampling for Dueling Bandits","created":"2016-04-25","cited_by_count":42},{"id":"2201.01985","title":"Jointly Efficient and Optimal Algorithms for Logistic Bandits","created":"2022-01-06","cited_by_count":41},{"id":"1902.10797","title":"Lipschitz Adaptivity with Multiple Learning Rates in Online Learning","created":"2019-02-27","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":"1506.00312","title":"Copeland Dueling Bandits","created":"2015-06-01","cited_by_count":36},{"id":"1706.00977","title":"Thompson Sampling for the MNL-Bandit","created":"2017-06-03","cited_by_count":35},{"id":"2010.14563","title":"Adversarial Dueling Bandits","created":"2020-10-27","cited_by_count":33},{"id":"1905.04654","title":"On the Performance of Thompson Sampling on Logistic Bandits","created":"2019-05-12","cited_by_count":32},{"id":"1306.6294","title":"Learning Trajectory Preferences for Manipulators via Iterative Improvement","created":"2013-06-26","cited_by_count":31},{"id":"1502.00133","title":"Sparse Dueling Bandits","created":"2015-01-31","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":"1810.13069","title":"Dynamic Assortment Optimization with Changing Contextual Information","created":"2018-10-31","cited_by_count":28},{"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":"2310.00968","title":"Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits","created":"2023-10-02","cited_by_count":22},{"id":"1801.01253","title":"Approximate Ranking from Pairwise Comparisons","created":"2018-01-04","cited_by_count":21},{"id":"2103.13929","title":"Multinomial Logit Contextual Bandits: Provable Optimality and Practicality","created":"2021-03-25","cited_by_count":21},{"id":"2110.10018","title":"Dynamic pricing and assortment under a contextual MNL demand","created":"2021-10-19","cited_by_count":20},{"id":"2405.09831","title":"Nearly Minimax Optimal Regret for Multinomial Logistic Bandit","created":"2024-05-16","cited_by_count":20},{"id":"1603.06390","title":"Learning Dynamic Robot-to-Human Object Handover from Human Feedback","created":"2016-03-21","cited_by_count":19},{"id":"2303.08816","title":"Borda Regret Minimization for Generalized Linear Dueling Bandits","created":"2023-03-15","cited_by_count":17},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17},{"id":"1605.01677","title":"Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm","created":"2016-05-05","cited_by_count":16},{"id":"1805.02971","title":"Multinomial Logit Bandit with Linear Utility Functions","created":"2018-05-08","cited_by_count":15},{"id":"2011.14033","title":"A Tractable Online Learning Algorithm for the Multinomial Logit Contextual Bandit","created":"2020-11-28","cited_by_count":15},{"id":"2502.10020","title":"Improved Online Confidence Bounds for Multinomial Logistic Bandits","created":"2025-02-14","cited_by_count":15},{"id":"2212.13540","title":"Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2022-12-27","cited_by_count":13},{"id":"1601.05495","title":"Data-driven Rank Breaking for Efficient Rank Aggregation","created":"2016-01-21","cited_by_count":10},{"id":"2503.01076","title":"Active Learning for Direct Preference Optimization","created":"2025-03-03","cited_by_count":10},{"id":"2405.20165","title":"Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2024-05-30","cited_by_count":7},{"id":"2402.18917","title":"Stop Relying on No-Choice and Do not Repeat the Moves: Optimal, Efficient and Practical Algorithms for Assortment Optimization","created":"2024-02-29","cited_by_count":4},{"id":"2502.10158","title":"Combinatorial Reinforcement Learning with Preference Feedback","created":"2025-02-14","cited_by_count":2}],"next_cursor":null}