{"total":51,"rows":[{"id":"2102.06129","title":"Meta-Thompson Sampling","created":"2021-02-11","cited_by_count":63,"area":null},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2309.17382","title":"Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency","created":"2023-09-29","cited_by_count":46,"area":"wm"},{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2107.06196","title":"No Regrets for Learning the Prior in Bandits","created":"2021-07-13","cited_by_count":30,"area":null},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2105.14267","title":"Information Directed Sampling for Sparse Linear Bandits","created":"2021-05-29","cited_by_count":20,"area":null},{"id":"2202.01454","title":"Deep Hierarchy in Bandits","created":"2022-02-03","cited_by_count":19,"area":null},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2504.20997","title":"Toward Efficient Exploration by Large Language Model Agents","created":"2025-04-29","cited_by_count":17,"area":"agents"},{"id":"2106.05608","title":"Thompson Sampling with a Mixture Prior","created":"2021-06-10","cited_by_count":16,"area":null},{"id":"2107.05320","title":"Metalearning Linear Bandits by Prior Update","created":"2021-07-12","cited_by_count":16,"area":null},{"id":"2107.07410","title":"PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration","created":"2021-07-15","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":"2405.20984","title":"Bayesian Design Principles for Offline-to-Online Reinforcement Learning","created":"2024-05-31","cited_by_count":14,"area":"offlinerl"},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","cited_by_count":13,"area":"offlinerl"},{"id":"2202.13227","title":"Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework","created":"2022-02-26","cited_by_count":11,"area":null},{"id":"2202.12888","title":"Meta-Learning for Simple Regret Minimization","created":"2022-02-25","cited_by_count":10,"area":null},{"id":"2207.06456","title":"Graph Neural Network Bandits","created":"2022-07-13","cited_by_count":10,"area":null},{"id":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","cited_by_count":10,"area":"deeprl"},{"id":"2212.04720","title":"Multi-Task Off-Policy Learning from Bandit Feedback","created":"2022-12-09","cited_by_count":9,"area":null},{"id":"2310.17769","title":"Social Contract AI: Aligning AI Assistants with Implicit Group Norms","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2305.11455","title":"Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models","created":"2023-05-19","cited_by_count":8,"area":"agents"},{"id":"2301.05182","title":"Thompson Sampling with Diffusion Generative Prior","created":"2023-01-12","cited_by_count":7,"area":"diffusion"},{"id":"2310.20007","title":"Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2210.16877","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","created":"2022-10-30","cited_by_count":6,"area":null},{"id":"2402.10228","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","created":"2024-02-05","cited_by_count":6,"area":"deeprl"},{"id":"2102.09488","title":"A Bit Better? Quantifying Information for Bandit Learning","created":"2021-02-18","cited_by_count":5,"area":null},{"id":"2201.01902","title":"Gaussian Imagination in Bandit Learning","created":"2022-01-06","cited_by_count":5,"area":null},{"id":"2402.10028","title":"Diffusion Models Meet Contextual Bandits","created":"2024-02-15","cited_by_count":5,"area":"diffusion"},{"id":"2510.14129","title":"Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL","created":"2025-10-15","cited_by_count":5,"area":"deeprl"},{"id":"2106.12200","title":"Random Effect Bandits","created":"2021-06-23","cited_by_count":4,"area":null},{"id":"2301.12038","title":"STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning","created":"2023-01-28","cited_by_count":4,"area":null},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2303.09033","title":"Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling","created":"2023-03-16","cited_by_count":3,"area":null},{"id":"2405.16581","title":"On Bits and Bandits: Quantifying the Regret-Information Trade-off","created":"2024-05-26","cited_by_count":3,"area":null},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2403.11175","title":"Prior-dependent analysis of posterior sampling reinforcement learning with function approximation","created":"2024-03-17","cited_by_count":2,"area":"deeprl"},{"id":"2404.19292","title":"Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2410.03919","title":"Online Posterior Sampling with a Diffusion Prior","created":"2024-10-04","cited_by_count":2,"area":"diffusion"},{"id":"2602.22523","title":"Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents","created":"2026-02-26","cited_by_count":2,"area":"agents"},{"id":"2106.07203","title":"Online Sub-Sampling for Reinforcement Learning with General Function Approximation","created":"2021-06-14","cited_by_count":1,"area":null},{"id":"2301.10651","title":"Overcoming Prior Misspecification in Online Learning to Rank","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2405.04910","title":"Learning with Posterior Sampling for Revenue Management under Time-varying Demand","created":"2024-05-08","cited_by_count":1,"area":null},{"id":"2603.15871","title":"Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement Learning","created":"2026-03-16","cited_by_count":1,"area":"deeprl"},{"id":"2301.03142","title":"Exploration in Model-based Reinforcement Learning with Randomized Reward","created":"2023-01-09","cited_by_count":0,"area":null},{"id":"2306.09136","title":"Finite-Time Logarithmic Bayes Regret Upper Bounds","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2309.01453","title":"Interactive Graph Convolutional Filtering","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2604.02349","title":"OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2609.33246","title":"Minimax-Optimality of Posterior Sampling for Reinforcement Learning","created":"2026-09-27","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}