{"list":"other","total":73,"rows":[{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"2303.06865","title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","created":"2023-03-13","cited_by_count":575},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279},{"id":"2106.06926","title":"Bellman-consistent Pessimism for Offline Reinforcement Learning","created":"2021-06-13","cited_by_count":269},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268},{"id":"2107.00591","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","created":"2021-07-01","cited_by_count":214},{"id":"1912.02074","title":"AlgaeDICE: Policy Gradient from Arbitrary Experience","created":"2019-12-04","cited_by_count":188},{"id":"2410.03834","title":"GraphRouter: A Graph-based Router for LLM Selections","created":"2024-10-04","cited_by_count":165},{"id":"1909.01150","title":"Neural Policy Gradient Methods: Global Optimality and Rates of Convergence","created":"2019-08-29","cited_by_count":159},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110},{"id":"2202.13890","title":"Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity","created":"2022-02-28","cited_by_count":85},{"id":"2204.05275","title":"Settling the Sample Complexity of Model-Based Offline Reinforcement Learning","created":"2022-04-11","cited_by_count":83},{"id":"1407.8339","title":"Combinatorial Multi-Armed Bandit and Its Extension to Probabilistically Triggered Arms","created":"2014-07-31","cited_by_count":79},{"id":"1803.04623","title":"Thompson Sampling for Combinatorial Semi-Bandits","created":"2018-03-13","cited_by_count":78},{"id":"1502.02763","title":"Cascading Bandits: Learning to Rank in the Cascade Model","created":"2015-02-10","cited_by_count":77},{"id":"1901.04891","title":"Combinatorial Sleeping Bandits with Fairness Constraints","created":"2019-01-15","cited_by_count":68},{"id":"2102.01748","title":"Near-Optimal Offline Reinforcement Learning via Double Variance Reduction","created":"2021-02-02","cited_by_count":56},{"id":"1901.08779","title":"Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously","created":"2019-01-25","cited_by_count":53},{"id":"1706.03880","title":"MNL-Bandit: A Dynamic Learning Approach to Assortment Selection","created":"2017-06-13","cited_by_count":50},{"id":"1703.01610","title":"Improving Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms and Its Applications","created":"2017-03-05","cited_by_count":45},{"id":"1507.04208","title":"Combinatorial Cascading Bandits","created":"2015-07-15","cited_by_count":40},{"id":"2102.11050","title":"Online Learning via Offline Greedy Algorithms: Applications in Market Design and Optimization","created":"2021-02-18","cited_by_count":40},{"id":"2405.16587","title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","created":"2024-05-26","cited_by_count":39},{"id":"1806.02248","title":"TopRank: A practical algorithm for online stochastic ranking","created":"2018-06-06","cited_by_count":30},{"id":"2211.00716","title":"Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian","created":"2022-11-01","cited_by_count":29},{"id":"1502.06354","title":"First-order regret bounds for combinatorial semi-bandits","created":"2015-02-23","cited_by_count":26},{"id":"2111.13807","title":"Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization","created":"2021-11-27","cited_by_count":25},{"id":"1903.00543","title":"Combinatorial Bandits with Relative Feedback","created":"2019-03-01","cited_by_count":19},{"id":"1905.13341","title":"On Value Functions and the Agent-Environment Boundary","created":"2019-05-30","cited_by_count":19},{"id":"2301.13326","title":"A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback","created":"2023-01-30","cited_by_count":19},{"id":"2302.01324","title":"Randomized Greedy Learning for Non-monotone Stochastic Submodular Maximization Under Full-bandit Feedback","created":"2023-02-02","cited_by_count":19},{"id":"2205.10671","title":"Pessimism for Offline Linear Contextual Bandits using $\\ell_p$ Confidence Sets","created":"2022-05-21","cited_by_count":18},{"id":"2303.17110","title":"Contextual Combinatorial Bandits with Probabilistically Triggered Arms","created":"2023-03-30","cited_by_count":18},{"id":"2312.08057","title":"Combinatorial Stochastic-Greedy Bandit","created":"2023-12-13","cited_by_count":18},{"id":"2306.00242","title":"Combinatorial Neural Bandits","created":"2023-05-31","cited_by_count":16},{"id":"2208.14837","title":"Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms","created":"2022-08-31","cited_by_count":15},{"id":"1905.03125","title":"Batch-Size Independent Regret Bounds for the Combinatorial Multi-Armed Bandit Problem","created":"2019-05-08","cited_by_count":14},{"id":"2101.01301","title":"Adversarial Combinatorial Bandits with General Non-linear Reward Functions","created":"2021-01-05","cited_by_count":14},{"id":"1512.06238","title":"The Limitations of Optimization from Samples","created":"2015-12-19","cited_by_count":13},{"id":"2405.05950","title":"Federated Combinatorial Multi-Agent Multi-Armed Bandits","created":"2024-05-09","cited_by_count":11},{"id":"1906.03737","title":"Factorization Bandits for Online Influence Maximization","created":"2019-06-09","cited_by_count":10},{"id":"2105.04373","title":"Combinatorial Multi-armed Bandits for Resource Allocation","created":"2021-05-10","cited_by_count":10},{"id":"2203.12577","title":"Minimax Regret for Cascading Bandits","created":"2022-03-23","cited_by_count":10},{"id":"2308.11336","title":"On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems","created":"2023-08-22","cited_by_count":10},{"id":"2106.03403","title":"Network Inference and Influence Maximization from Samples","created":"2021-06-07","cited_by_count":9},{"id":"2501.01849","title":"A Multi-Agent Conversational Bandit Approach to Online Evaluation and Selection of User-Aligned LLM Responses","created":"2025-01-03","cited_by_count":8},{"id":"2406.01386","title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","created":"2024-06-03","cited_by_count":7},{"id":"2007.02738","title":"Optimization from Structured Samples for Coverage Functions","created":"2020-07-06","cited_by_count":6},{"id":"2106.05065","title":"Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning","created":"2021-06-09","cited_by_count":6},{"id":"2106.15808","title":"Optimal Epidemic Control as a Contextual Combinatorial Bandit with Budget","created":"2021-06-30","cited_by_count":5},{"id":"2306.07528","title":"Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective","created":"2023-06-13","cited_by_count":4},{"id":"1703.00557","title":"Model-Independent Online Learning for Influence Maximization","created":"2017-03-01","cited_by_count":3},{"id":"2305.16074","title":"Combinatorial Bandits for Maximum Value Reward Function under Max Value-Index Feedback","created":"2023-05-25","cited_by_count":3},{"id":"2410.17075","title":"Combinatorial Logistic Bandits","created":"2024-10-22","cited_by_count":3}],"next_cursor":null}