{"total":168,"rows":[{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364,"area":"offlinerl"},{"id":"2509.06941","title":"Outcome-based Exploration for LLM Reasoning","created":"2025-09-08","cited_by_count":83,"area":"lr"},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2206.04771","title":"Joint Entropy Search for Maximally-Informed Bayesian Optimization","created":"2022-06-09","cited_by_count":55,"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":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45,"area":null},{"id":"2206.13063","title":"On the Complexity of Adversarial Decision Making","created":"2022-06-27","cited_by_count":33,"area":null},{"id":"2302.09205","title":"Approximate Thompson Sampling via Epistemic Neural Networks","created":"2023-02-18","cited_by_count":31,"area":null},{"id":"2301.08215","title":"Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient","created":"2023-01-19","cited_by_count":30,"area":null},{"id":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"area":"deeprl"},{"id":"2107.09224","title":"From Predictions to Decisions: The Importance of Joint Predictive Distributions","created":"2021-07-20","cited_by_count":29,"area":null},{"id":"2407.13977","title":"A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits","created":"2024-07-19","cited_by_count":29,"area":null},{"id":"2102.12466","title":"Information Directed Reward Learning for Reinforcement Learning","created":"2021-02-24","cited_by_count":24,"area":"alignment"},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2101.06197","title":"Deciding What to Learn: A Rate-Distortion Approach","created":"2021-01-15","cited_by_count":23,"area":null},{"id":"2205.07704","title":"From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses","created":"2022-05-16","cited_by_count":22,"area":null},{"id":"2205.01970","title":"Non-Stationary Bandit Learning via Predictive Sampling","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2411.00062","title":"Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play","created":"2024-10-31","cited_by_count":21,"area":"alignment"},{"id":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","cited_by_count":20,"area":null},{"id":"2105.14267","title":"Information Directed Sampling for Sparse Linear Bandits","created":"2021-05-29","cited_by_count":20,"area":null},{"id":"2205.13924","title":"Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits","created":"2022-05-27","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":"2310.00806","title":"Bayesian Design Principles for Frequentist Sequential Learning","created":"2023-10-01","cited_by_count":18,"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":"2107.05320","title":"Metalearning Linear Bandits by Prior Update","created":"2021-07-12","cited_by_count":16,"area":null},{"id":"2112.05244","title":"An Experimental Design Perspective on Model-Based Reinforcement Learning","created":"2021-12-09","cited_by_count":16,"area":null},{"id":"2205.10895","title":"Contextual Information-Directed Sampling","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2110.13973","title":"The Value of Information When Deciding What to Learn","created":"2021-10-26","cited_by_count":15,"area":null},{"id":"2205.12086","title":"Information-Directed Selection for Top-Two Algorithms","created":"2022-05-24","cited_by_count":15,"area":null},{"id":"2109.12509","title":"Deep Exploration for Recommendation Systems","created":"2021-09-26","cited_by_count":14,"area":null},{"id":"2202.10997","title":"Minimax Regret for Partial Monitoring: Infinite Outcomes and Rustichini's Regret","created":"2022-02-22","cited_by_count":14,"area":null},{"id":"2201.11817","title":"Modeling Human Exploration Through Resource-Rational Reinforcement Learning","created":"2022-01-27","cited_by_count":13,"area":null},{"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":"2211.08572","title":"Bayesian Fixed-Budget Best-Arm Identification","created":"2022-11-15","cited_by_count":13,"area":null},{"id":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2506.01393","title":"Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization","created":"2025-06-02","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":"2106.01660","title":"Bandit Phase Retrieval","created":"2021-06-03","cited_by_count":12,"area":null},{"id":"2106.08414","title":"On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control","created":"2021-06-15","cited_by_count":12,"area":null},{"id":"2209.14414","title":"Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2302.03683","title":"Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2506.05295","title":"Sample Complexity and Representation Ability of Test-time Scaling Paradigms","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2105.11802","title":"Bias-Robust Bayesian Optimization via Dueling Bandits","created":"2021-05-25","cited_by_count":11,"area":null},{"id":"2111.09885","title":"Rate-optimal Bayesian Simple Regret in Best Arm Identification","created":"2021-11-18","cited_by_count":11,"area":null},{"id":"2302.04452","title":"An Information-Theoretic Analysis of Nonstationary Bandit Learning","created":"2023-02-09","cited_by_count":11,"area":null},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2302.05371","title":"A Second-Order Method for Stochastic Bandit Convex Optimisation","created":"2023-02-10","cited_by_count":10,"area":null},{"id":"2302.12202","title":"A Definition of Non-Stationary Bandits","created":"2023-02-23","cited_by_count":9,"area":null},{"id":"2502.19006","title":"Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2202.09036","title":"Adaptive Experimentation in the Presence of Exogenous Nonstationary Variation","created":"2022-02-18","cited_by_count":8,"area":null},{"id":"2210.04642","title":"Exploration via Planning for Information about the Optimal Trajectory","created":"2022-10-06","cited_by_count":8,"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":"2401.17037","title":"Enhancing Gaussian Process Surrogates for Optimization and Posterior Approximation via Random Exploration","created":"2024-01-30","cited_by_count":8,"area":null},{"id":"2302.06025","title":"Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits","created":"2023-02-12","cited_by_count":7,"area":null},{"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":"2402.15411","title":"Optimistic Information Directed Sampling","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2602.06448","title":"Principle-Evolvable Scientific Discovery via Uncertainty Minimization","created":"2026-02-06","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":"2304.05365","title":"Did we personalize? Assessing personalization by an online reinforcement learning algorithm using resampling","created":"2023-04-11","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":"2404.17493","title":"Causally Abstracted Multi-armed Bandits","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2406.13909","title":"Beyond Optimism: Exploration With Partially Observable Rewards","created":"2024-06-20","cited_by_count":6,"area":"deeprl"},{"id":"2502.07064","title":"Contextual Thompson Sampling via Generation of Missing Data","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2506.12751","title":"Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions","created":"2025-06-15","cited_by_count":6,"area":null},{"id":"2601.22538","title":"Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Models","created":"2026-01-30","cited_by_count":6,"area":null},{"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":"2209.02211","title":"Multi-Armed Bandits with Self-Information Rewards","created":"2022-09-06","cited_by_count":5,"area":null},{"id":"2303.11369","title":"Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale","created":"2023-03-20","cited_by_count":5,"area":"offlinerl"},{"id":"2304.13593","title":"Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards","created":"2023-04-26","cited_by_count":5,"area":null},{"id":"2101.09178","title":"Estimating $\\alpha$-Rank by Maximizing Information Gain","created":"2021-01-22","cited_by_count":4,"area":null},{"id":"2210.14972","title":"Environment Design for Inverse Reinforcement Learning","created":"2022-10-26","cited_by_count":4,"area":"offlinerl"},{"id":"2210.15513","title":"Lifelong Bandit Optimization: No Prior and No Regret","created":"2022-10-27","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":"2403.04764","title":"TS-RSR: A provably efficient approach for batch Bayesian Optimization","created":"2024-03-07","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":"2408.06542","title":"Value of Information and Reward Specification in Active Inference and POMDPs","created":"2024-08-13","cited_by_count":4,"area":null},{"id":"2502.05434","title":"Sample-Efficient Reinforcement Learning from Human Feedback via Information-Directed Sampling","created":"2025-02-08","cited_by_count":4,"area":"alignment"},{"id":"2507.09828","title":"Regret Analysis of Posterior Sampling-Based Expected Improvement for Bayesian Optimization","created":"2025-07-13","cited_by_count":4,"area":null},{"id":"2509.20648","title":"Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2106.00444","title":"Minimax Regret for Bandit Convex Optimisation of Ridge Functions","created":"2021-06-01","cited_by_count":3,"area":null},{"id":"2109.14412","title":"Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification","created":"2021-09-29","cited_by_count":3,"area":null},{"id":"2202.05767","title":"A PDE-Based Analysis of the Symmetric Two-Armed Bernoulli Bandit","created":"2022-02-11","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":"2410.04988","title":"Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling","created":"2024-10-07","cited_by_count":3,"area":"deeprl"},{"id":"2102.04263","title":"Generalised correlated batched bandits via the ARC algorithm with application to dynamic pricing","created":"2021-02-08","cited_by_count":2,"area":null},{"id":"2105.04683","title":"Deep Bandits Show-Off: Simple and Efficient Exploration with Deep Networks","created":"2021-05-10","cited_by_count":2,"area":null},{"id":"2203.04192","title":"Reward-Biased Maximum Likelihood Estimation for Neural Contextual Bandits","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2205.14829","title":"Adaptive Sampling for Discovery","created":"2022-05-30","cited_by_count":2,"area":null},{"id":"2207.03635","title":"Information-Gathering in Latent Bandits","created":"2022-07-08","cited_by_count":2,"area":null},{"id":"2302.06916","title":"Effective Dimension in Bandit Problems under Censorship","created":"2023-02-14","cited_by_count":2,"area":null},{"id":"2401.05015","title":"An Information Theoretic Approach to Interaction-Grounded Learning","created":"2024-01-10","cited_by_count":2,"area":"deeprl"},{"id":"2403.10379","title":"Regret Minimization via Saddle Point Optimization","created":"2024-03-15","cited_by_count":2,"area":null},{"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":"2405.15031","title":"Amortized nonmyopic active search via deep imitation learning","created":"2024-05-23","cited_by_count":2,"area":"offlinerl"},{"id":"2405.15090","title":"Pure Exploration for Constrained Best Mixed Arm Identification with a Fixed Budget","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2405.15200","title":"Indexed Minimum Empirical Divergence-Based Algorithms for Linear Bandits","created":"2024-05-24","cited_by_count":2,"area":null},{"id":"2410.14807","title":"Aligning AI Agents via Information-Directed Sampling","created":"2024-10-18","cited_by_count":2,"area":"alignment"}],"next_cursor":"100"}