{"total":481,"rows":[{"id":"2403.15371","title":"Can large language models explore in-context?","created":"2024-03-22","cited_by_count":76,"area":null},{"id":"2303.01859","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","created":"2023-03-03","cited_by_count":62,"area":null},{"id":"2108.09262","title":"Optimal Order Simple Regret for Gaussian Process Bandits","created":"2021-08-20","cited_by_count":54,"area":null},{"id":"2202.06317","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","created":"2022-02-13","cited_by_count":54,"area":null},{"id":"2102.04692","title":"Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2111.12306","title":"Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability","created":"2021-11-24","cited_by_count":44,"area":null},{"id":"2103.02735","title":"Fairness of Exposure in Stochastic Bandits","created":"2021-03-03","cited_by_count":43,"area":null},{"id":"2504.16078","title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities","created":"2025-04-22","cited_by_count":41,"area":"agents"},{"id":"2405.16587","title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","created":"2024-05-26","cited_by_count":39,"area":"alignment"},{"id":"2405.16420","title":"M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions","created":"2024-05-26","cited_by_count":38,"area":"rag"},{"id":"2502.10550","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","created":"2025-02-14","cited_by_count":36,"area":"deeprl"},{"id":"2510.17845","title":"MAT-Agent: Adaptive Multi-Agent Training Optimization","created":"2025-10-10","cited_by_count":35,"area":null},{"id":"2203.13935","title":"Offline Reinforcement Learning Under Value and Density-Ratio Realizability: The Power of Gaps","created":"2022-03-25","cited_by_count":34,"area":"offlinerl"},{"id":"2410.06238","title":"EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration","created":"2024-10-08","cited_by_count":34,"area":"lr"},{"id":"2502.19918","title":"Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":33,"area":"lr"},{"id":"2406.03853","title":"Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism","created":"2024-06-06","cited_by_count":32,"area":"inference"},{"id":"2502.17543","title":"Training a Generally Curious Agent","created":"2025-02-24","cited_by_count":31,"area":"agents"},{"id":"2103.07501","title":"Beyond $\\log^2(T)$ Regret for Decentralized Bandits in Matching Markets","created":"2021-03-12","cited_by_count":30,"area":null},{"id":"2211.07484","title":"Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression","created":"2022-11-14","cited_by_count":30,"area":null},{"id":"2106.03365","title":"Generalized Linear Bandits with Local Differential Privacy","created":"2021-06-07","cited_by_count":29,"area":null},{"id":"2109.12974","title":"Bilateral Trade: A Regret Minimization Perspective","created":"2021-09-08","cited_by_count":29,"area":null},{"id":"2208.09407","title":"Learning in Stackelberg Games with Non-myopic Agents","created":"2022-08-19","cited_by_count":29,"area":null},{"id":"2501.17974","title":"Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization","created":"2025-01-29","cited_by_count":29,"area":"lr"},{"id":"2112.13838","title":"Tracking Most Significant Arm Switches in Bandits","created":"2021-12-27","cited_by_count":27,"area":null},{"id":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2306.03928","title":"Designing Decision Support Systems Using Counterfactual Prediction Sets","created":"2023-06-06","cited_by_count":26,"area":null},{"id":"2307.07539","title":"On the Sublinear Regret of GP-UCB","created":"2023-07-14","cited_by_count":26,"area":null},{"id":"2103.10246","title":"Stochastic Bandits for Multi-platform Budget Optimization in Online Advertising","created":"2021-03-16","cited_by_count":25,"area":null},{"id":"2104.04103","title":"Causal Decision Making and Causal Effect Estimation Are Not the Same... and Why It Matters","created":"2021-04-08","cited_by_count":25,"area":null},{"id":"2510.04996","title":"Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives","created":"2025-10-06","cited_by_count":25,"area":"lr"},{"id":"2101.04667","title":"Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information","created":"2021-01-12","cited_by_count":23,"area":null},{"id":"2401.16198","title":"Contracting with a Learning Agent","created":"2024-01-29","cited_by_count":23,"area":null},{"id":"2502.19732","title":"Speculative Decoding and Beyond: An In-Depth Survey of Techniques","created":"2025-02-27","cited_by_count":23,"area":"inference"},{"id":"2102.13028","title":"Batched Neural Bandits","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2210.01898","title":"Replicable Bandits","created":"2022-10-04","cited_by_count":22,"area":null},{"id":"2404.12526","title":"Adaptive Memory Replay for Continual Learning","created":"2024-04-18","cited_by_count":22,"area":null},{"id":"2504.16918","title":"OptimAI: Optimization from Natural Language Using LLM-Powered AI Agents","created":"2025-04-23","cited_by_count":22,"area":"agents"},{"id":"2106.01420","title":"Parallelizing Thompson Sampling","created":"2021-06-02","cited_by_count":20,"area":null},{"id":"2301.13306","title":"Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics","created":"2023-01-30","cited_by_count":20,"area":null},{"id":"2102.08754","title":"A Regret Analysis of Bilateral Trade","created":"2021-02-16","cited_by_count":19,"area":null},{"id":"2206.00826","title":"BayesFormer: Transformer with Uncertainty Estimation","created":"2022-06-02","cited_by_count":19,"area":null},{"id":"2211.16275","title":"A survey on multi-player bandits","created":"2022-11-29","cited_by_count":19,"area":null},{"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,"area":null},{"id":"2412.06126","title":"UCB algorithms for multi-armed bandits: Precise regret and adaptive inference","created":"2024-12-09","cited_by_count":19,"area":null},{"id":"2205.13930","title":"Fairness and Welfare Quantification for Regret in Multi-Armed Bandits","created":"2022-05-27","cited_by_count":17,"area":null},{"id":"2307.09943","title":"Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay","created":"2023-07-19","cited_by_count":17,"area":null},{"id":"2310.12370","title":"No-Regret Learning in Bilateral Trade via Global Budget Balance","created":"2023-10-18","cited_by_count":17,"area":null},{"id":"2207.07974","title":"Online Prediction in Sub-linear Space","created":"2022-07-16","cited_by_count":16,"area":null},{"id":"2210.06846","title":"An $\\alpha$-regret analysis of Adversarial Bilateral Trade","created":"2022-10-13","cited_by_count":16,"area":null},{"id":"2107.02772","title":"A Causal Bandit Approach to Learning Good Atomic Interventions in Presence of Unobserved Confounders","created":"2021-07-06","cited_by_count":15,"area":null},{"id":"2112.00195","title":"Efficient Online Bayesian Inference for Neural Bandits","created":"2021-12-01","cited_by_count":15,"area":null},{"id":"2202.13234","title":"Safe Exploration for Efficient Policy Evaluation and Comparison","created":"2022-02-26","cited_by_count":15,"area":null},{"id":"2305.18543","title":"Robust Lipschitz Bandits to Adversarial Corruptions","created":"2023-05-29","cited_by_count":15,"area":null},{"id":"2306.07923","title":"Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits","created":"2023-06-13","cited_by_count":15,"area":"offlinerl"},{"id":"2307.09478","title":"The Role of Transparency in Repeated First-Price Auctions with Unknown Valuations","created":"2023-07-14","cited_by_count":15,"area":null},{"id":"2310.03525","title":"Vehicle-to-Everything Cooperative Perception for Autonomous Driving","created":"2023-10-05","cited_by_count":15,"area":null},{"id":"2403.12948","title":"On Safety in Safe Bayesian Optimization","created":"2024-03-19","cited_by_count":15,"area":null},{"id":"2102.03803","title":"Lazy OCO: Online Convex Optimization on a Switching Budget","created":"2021-02-07","cited_by_count":14,"area":null},{"id":"2205.10032","title":"Survey on Fair Reinforcement Learning: Theory and Practice","created":"2022-05-20","cited_by_count":14,"area":null},{"id":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2302.01523","title":"Multi-channel Autobidding with Budget and ROI Constraints","created":"2023-02-03","cited_by_count":14,"area":null},{"id":"2606.01619","title":"ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL","created":"2026-06-01","cited_by_count":14,"area":"agents"},{"id":"2210.00025","title":"Artificial Replay: A Meta-Algorithm for Harnessing Historical Data in Bandits","created":"2022-09-30","cited_by_count":13,"area":null},{"id":"2211.08586","title":"Bandit Algorithms for Prophet Inequality and Pandora's Box","created":"2022-11-16","cited_by_count":13,"area":null},{"id":"2301.12366","title":"Smooth Non-Stationary Bandits","created":"2023-01-29","cited_by_count":13,"area":null},{"id":"2304.01781","title":"Mixing predictions for online metric algorithms","created":"2023-04-04","cited_by_count":13,"area":null},{"id":"2403.03811","title":"Incentivized Learning in Principal-Agent Bandit Games","created":"2024-03-06","cited_by_count":13,"area":null},{"id":"2101.08699","title":"An empirical evaluation of active inference in multi-armed bandits","created":"2021-01-21","cited_by_count":12,"area":null},{"id":"2106.04700","title":"Scale Free Adversarial Multi Armed Bandits","created":"2021-06-08","cited_by_count":12,"area":null},{"id":"2110.15843","title":"Adaptive Discretization in Online Reinforcement Learning","created":"2021-10-29","cited_by_count":12,"area":null},{"id":"2205.00984","title":"A Sharp Memory-Regret Trade-Off for Multi-Pass Streaming Bandits","created":"2022-05-02","cited_by_count":12,"area":null},{"id":"2209.12013","title":"Non-monotonic Resource Utilization in the Bandits with Knapsacks Problem","created":"2022-09-24","cited_by_count":12,"area":null},{"id":"2210.11834","title":"Optimal Contextual Bandits with Knapsacks under Realizability via Regression Oracles","created":"2022-10-21","cited_by_count":12,"area":null},{"id":"2306.04375","title":"Learning via Wasserstein-Based High Probability Generalisation Bounds","created":"2023-06-07","cited_by_count":12,"area":null},{"id":"2306.14834","title":"Scalable Neural Contextual Bandit for Recommender Systems","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2310.04550","title":"Module-wise Adaptive Distillation for Multimodality Foundation Models","created":"2023-10-06","cited_by_count":12,"area":null},{"id":"2406.19317","title":"Jump Starting Bandits with LLM-Generated Prior Knowledge","created":"2024-06-27","cited_by_count":12,"area":null},{"id":"2103.00360","title":"Exploration and Incentives in Reinforcement Learning","created":"2021-02-28","cited_by_count":11,"area":null},{"id":"2105.13059","title":"Efficient and Generalizable Tuning Strategies for Stochastic Gradient MCMC","created":"2021-05-27","cited_by_count":11,"area":null},{"id":"2109.08792","title":"Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making","created":"2021-09-18","cited_by_count":11,"area":null},{"id":"2203.13423","title":"Modeling Attrition in Recommender Systems with Departing Bandits","created":"2022-03-25","cited_by_count":11,"area":null},{"id":"2206.02344","title":"Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets","created":"2022-06-06","cited_by_count":11,"area":null},{"id":"2207.11126","title":"Optimism in Face of a Context: Regret Guarantees for Stochastic Contextual MDP","created":"2022-07-22","cited_by_count":11,"area":null},{"id":"2306.05579","title":"Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards","created":"2023-06-08","cited_by_count":11,"area":null},{"id":"2405.05950","title":"Federated Combinatorial Multi-Agent Multi-Armed Bandits","created":"2024-05-09","cited_by_count":11,"area":null},{"id":"2501.05673","title":"Network Diffuser for Placing-Scheduling Service Function Chains with Inverse Demonstration","created":"2025-01-10","cited_by_count":11,"area":null},{"id":"2504.07157","title":"GAAPO: Genetic Algorithmic Applied to Prompt Optimization","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2109.03150","title":"Recommendation Fairness: From Static to Dynamic","created":"2021-09-05","cited_by_count":10,"area":null},{"id":"2206.09341","title":"Bayesian Optimization under Stochastic Delayed Feedback","created":"2022-06-19","cited_by_count":10,"area":null},{"id":"2209.11817","title":"An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regret","created":"2022-09-23","cited_by_count":10,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2306.17815","title":"Bayesian Optimization with Formal Safety Guarantees via Online Conformal Prediction","created":"2023-06-30","cited_by_count":10,"area":null},{"id":"2312.14037","title":"Neural Contextual Bandits for Personalized Recommendation","created":"2023-12-21","cited_by_count":10,"area":null},{"id":"2403.13674","title":"Reward-Driven Automated Curriculum Learning for Interaction-Aware Self-Driving at Unsignalized Intersections","created":"2024-03-20","cited_by_count":10,"area":"driving"},{"id":"2410.12846","title":"Accurate and Regret-aware Numerical Problem Solver for Tabular Question Answering","created":"2024-10-10","cited_by_count":10,"area":null},{"id":"2107.00680","title":"A Map of Bandits for E-commerce","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2109.08467","title":"Online Learning of Network Bottlenecks via Minimax Paths","created":"2021-09-17","cited_by_count":9,"area":null},{"id":"2201.09353","title":"Distributed Bandits with Heterogeneous Agents","created":"2022-01-23","cited_by_count":9,"area":null},{"id":"2206.00494","title":"Incentivizing Combinatorial Bandit Exploration","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2206.13606","title":"Online Resource Allocation under Horizon Uncertainty","created":"2022-06-27","cited_by_count":9,"area":null}],"next_cursor":"100"}