{"list":"other","total":56,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"1603.00943","title":"CVXPY: A Python-Embedded Modeling Language for Convex Optimization","created":"2016-03-03","cited_by_count":641},{"id":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"2009.00236","title":"A Survey of Deep Active Learning","created":"2020-08-30","cited_by_count":554},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","created":"2022-12-19","cited_by_count":333},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"1503.02834","title":"Doubly Robust Policy Evaluation and Optimization","created":"2015-03-10","cited_by_count":158},{"id":"2010.09535","title":"Cold-start Active Learning through Self-supervised Language Modeling","created":"2020-10-19","cited_by_count":128},{"id":"2002.04833","title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","created":"2020-02-12","cited_by_count":120},{"id":"1304.6480","title":"A Theoretical Analysis of NDCG Type Ranking Measures","created":"2013-04-24","cited_by_count":119},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106},{"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":"1409.6110","title":"Best-Arm Identification in Linear Bandits","created":"2014-09-22","cited_by_count":100},{"id":"2306.14111","title":"Is RLHF More Difficult than Standard RL?","created":"2023-06-25","cited_by_count":96},{"id":"1906.08399","title":"Sequential Experimental Design for Transductive Linear Bandits","created":"2019-06-20","cited_by_count":91},{"id":"2106.09675","title":"Gone Fishing: Neural Active Learning with Fisher Embeddings","created":"2021-06-17","cited_by_count":88},{"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":"1502.02763","title":"Cascading Bandits: Learning to Rank in the Cascade Model","created":"2015-02-10","cited_by_count":77},{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71},{"id":"2305.15363","title":"Inverse Preference Learning: Preference-based RL without a Reward Function","created":"2023-05-24","cited_by_count":68},{"id":"2006.08910","title":"Preference-based Reinforcement Learning with Finite-Time Guarantees","created":"2020-06-16","cited_by_count":65},{"id":"2402.10500","title":"Active Preference Optimization for Sample Efficient RLHF","created":"2024-02-16","cited_by_count":62},{"id":"1908.01289","title":"Dueling Posterior Sampling for Preference-Based Reinforcement Learning","created":"2019-08-04","cited_by_count":56},{"id":"2310.14554","title":"Making RL with Preference-based Feedback Efficient via Randomization","created":"2023-10-23","cited_by_count":46},{"id":"1603.05359","title":"Cascading Bandits for Large-Scale Recommendation Problems","created":"2016-03-17","cited_by_count":45},{"id":"2006.11685","title":"An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits","created":"2020-06-21","cited_by_count":45},{"id":"2111.12306","title":"Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability","created":"2021-11-24","cited_by_count":44},{"id":"2305.16217","title":"Beyond Reward: Offline Preference-guided Policy Optimization","created":"2023-05-25","cited_by_count":35},{"id":"2105.13017","title":"Minimax Optimal Fixed-Budget Best Arm Identification in Linear Bandits","created":"2021-05-27","cited_by_count":32},{"id":"1806.02248","title":"TopRank: A practical algorithm for online stochastic ranking","created":"2018-06-06","cited_by_count":30},{"id":"1606.02448","title":"Multiple-Play Bandits in the Position-Based Model","created":"2016-06-08","cited_by_count":28},{"id":"1703.02527","title":"Online Learning to Rank in Stochastic Click Models","created":"2017-03-07","cited_by_count":26},{"id":"2305.18505","title":"Provable Reward-Agnostic Preference-Based Reinforcement Learning","created":"2023-05-29","cited_by_count":25},{"id":"2106.04763","title":"Fixed-Budget Best-Arm Identification in Structured Bandits","created":"2021-06-09","cited_by_count":22},{"id":"2302.01513","title":"Towards Practical Preferential Bayesian Optimization with Skew Gaussian Processes","created":"2023-02-03","cited_by_count":19},{"id":"2402.05367","title":"Principled Preferential Bayesian Optimization","created":"2024-02-08","cited_by_count":16},{"id":"2105.06499","title":"Improved Algorithms for Agnostic Pool-based Active Classification","created":"2021-05-13","cited_by_count":15},{"id":"2012.08073","title":"Chernoff Sampling for Active Testing and Extension to Active Regression","created":"2020-12-15","cited_by_count":13},{"id":"2106.12034","title":"Pure Exploration in Kernel and Neural Bandits","created":"2021-06-22","cited_by_count":13},{"id":"1911.00980","title":"Zeroth Order Non-convex optimization with Dueling-Choice Bandits","created":"2019-11-03","cited_by_count":11},{"id":"2105.11802","title":"Bias-Robust Bayesian Optimization via Dueling Bandits","created":"2021-05-25","cited_by_count":11},{"id":"2004.13106","title":"Learning to Rank in the Position Based Model with Bandit Feedback","created":"2020-04-27","cited_by_count":10},{"id":"2202.02407","title":"An Experimental Design Approach for Regret Minimization in Logistic Bandits","created":"2022-02-04","cited_by_count":7},{"id":"2006.06372","title":"TS-UCB: Improving on Thompson Sampling With Little to No Additional Computation","created":"2020-06-11","cited_by_count":6},{"id":"2202.06694","title":"Versatile Dueling Bandits: Best-of-both-World Analyses for Online Learning from Preferences","created":"2022-02-14","cited_by_count":5},{"id":"1906.07611","title":"Simple Algorithms for Dueling Bandits","created":"2019-06-18","cited_by_count":3},{"id":"2311.04528","title":"Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments","created":"2023-11-08","cited_by_count":2}],"next_cursor":null}