{"total":433,"rows":[{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120,"area":null},{"id":"2402.12275","title":"WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment","created":"2024-02-19","cited_by_count":107,"area":"wm"},{"id":"2208.06102","title":"Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training","created":"2022-08-12","cited_by_count":79,"area":null},{"id":"2206.03301","title":"Recent Advances in Bayesian Optimization","created":"2022-06-07","cited_by_count":76,"area":null},{"id":"2403.15371","title":"Can large language models explore in-context?","created":"2024-03-22","cited_by_count":76,"area":null},{"id":"2404.11599","title":"Variational Bayesian Last Layers","created":"2024-04-17","cited_by_count":69,"area":null},{"id":"2102.06129","title":"Meta-Thompson Sampling","created":"2021-02-11","cited_by_count":63,"area":null},{"id":"2402.00809","title":"Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI","created":"2024-02-01","cited_by_count":62,"area":null},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2405.17503","title":"Code Repair with LLMs gives an Exploration-Exploitation Tradeoff","created":"2024-05-26","cited_by_count":51,"area":null},{"id":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50,"area":null},{"id":"2201.09863","title":"Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots","created":"2022-01-24","cited_by_count":47,"area":null},{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45,"area":null},{"id":"2106.02029","title":"Off-Policy Evaluation via Adaptive Weighting with Data from Contextual Bandits","created":"2021-06-03","cited_by_count":40,"area":null},{"id":"2307.16212","title":"Robust Multi-Agent Reinforcement Learning with State Uncertainty","created":"2023-07-30","cited_by_count":36,"area":null},{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2510.17845","title":"MAT-Agent: Adaptive Multi-Agent Training Optimization","created":"2025-10-10","cited_by_count":35,"area":null},{"id":"2402.02746","title":"Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization","created":"2024-02-05","cited_by_count":34,"area":null},{"id":"2206.07659","title":"Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2212.09900","title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality","created":"2022-12-19","cited_by_count":32,"area":null},{"id":"2306.17693","title":"Thompson sampling for improved exploration in GFlowNets","created":"2023-06-30","cited_by_count":32,"area":null},{"id":"2302.09205","title":"Approximate Thompson Sampling via Epistemic Neural Networks","created":"2023-02-18","cited_by_count":31,"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":"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":"1906.03352","title":"Watch, Try, Learn: Meta-Learning from Demonstrations and Reward","created":"2019-06-07","cited_by_count":28,"area":"offlinerl"},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2108.06422","title":"Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models","created":"2021-08-13","cited_by_count":24,"area":null},{"id":"2110.11665","title":"Diversified Sampling for Batched Bayesian Optimization with Determinantal Point Processes","created":"2021-10-22","cited_by_count":24,"area":null},{"id":"2203.01303","title":"An Analysis of Ensemble Sampling","created":"2022-03-02","cited_by_count":24,"area":null},{"id":"2310.18554","title":"Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion","created":"2023-10-28","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":"2305.19535","title":"Low-rank extended Kalman filtering for online learning of neural networks from streaming data","created":"2023-05-31","cited_by_count":23,"area":null},{"id":"2102.13202","title":"Online Multi-Armed Bandits with Adaptive Inference","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2110.04629","title":"The Neural Testbed: Evaluating Joint Predictions","created":"2021-10-09","cited_by_count":22,"area":null},{"id":"2206.03944","title":"Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-implementation Guidelines","created":"2022-06-08","cited_by_count":22,"area":null},{"id":"2206.07870","title":"How to talk so AI will learn: Instructions, descriptions, and autonomy","created":"2022-06-16","cited_by_count":22,"area":null},{"id":"2206.11254","title":"Langevin Monte Carlo for Contextual Bandits","created":"2022-06-22","cited_by_count":22,"area":null},{"id":"2105.02344","title":"Policy Learning with Adaptively Collected Data","created":"2021-05-05","cited_by_count":21,"area":null},{"id":"2205.01970","title":"Non-Stationary Bandit Learning via Predictive Sampling","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2106.01420","title":"Parallelizing Thompson Sampling","created":"2021-06-02","cited_by_count":20,"area":null},{"id":"2505.15141","title":"BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms","created":"2025-05-21","cited_by_count":20,"area":"inference"},{"id":"2107.00783","title":"Reinforcement Learning for Feedback-Enabled Cyber Resilience","created":"2021-07-02","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":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2206.03633","title":"Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping","created":"2022-06-08","cited_by_count":19,"area":null},{"id":"2208.07406","title":"Reward Design For An Online Reinforcement Learning Algorithm Supporting Oral Self-Care","created":"2022-08-15","cited_by_count":18,"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":"2405.02449","title":"Quality-Weighted Vendi Scores And Their Application To Diverse Experimental Design","created":"2024-05-03","cited_by_count":17,"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":"2106.05335","title":"Online Learning for Stochastic Shortest Path Model via Posterior Sampling","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2306.09803","title":"Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization","created":"2023-06-16","cited_by_count":16,"area":null},{"id":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16,"area":"alignment"},{"id":"2601.02695","title":"EvoRoute: Experience-Driven Self-Routing LLM Agent Systems","created":"2026-01-06","cited_by_count":16,"area":"agents"},{"id":"2110.13973","title":"The Value of Information When Deciding What to Learn","created":"2021-10-26","cited_by_count":15,"area":null},{"id":"2111.11107","title":"Branching Time Active Inference: the theory and its generality","created":"2021-11-22","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":"2305.15877","title":"Exponential Smoothing for Off-Policy Learning","created":"2023-05-25","cited_by_count":15,"area":null},{"id":"2101.09855","title":"Weak Signal Asymptotics for Sequentially Randomized Experiments","created":"2021-01-25","cited_by_count":14,"area":null},{"id":"2102.03799","title":"Online Limited Memory Neural-Linear Bandits with Likelihood Matching","created":"2021-02-07","cited_by_count":14,"area":null},{"id":"2109.12509","title":"Deep Exploration for Recommendation Systems","created":"2021-09-26","cited_by_count":14,"area":null},{"id":"2203.07322","title":"Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation","created":"2022-03-14","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":"2506.16658","title":"Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards","created":"2025-06-20","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":"2201.11817","title":"Modeling Human Exploration Through Resource-Rational Reinforcement Learning","created":"2022-01-27","cited_by_count":13,"area":null},{"id":"2202.06891","title":"Counterfactual inference in sequential experiments","created":"2022-02-14","cited_by_count":13,"area":null},{"id":"2206.08736","title":"Generalised Policy Improvement with Geometric Policy Composition","created":"2022-06-17","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":"2311.07565","title":"Exploration via linearly perturbed loss minimisation","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2410.04461","title":"Improved Off-policy Reinforcement Learning in Biological Sequence Design","created":"2024-10-06","cited_by_count":13,"area":"deeprl"},{"id":"2506.10341","title":"Formalizing Learning from Language Feedback with Provable Guarantees","created":"2025-06-12","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":"2102.05793","title":"Lenient Regret and Good-Action Identification in Gaussian Process Bandits","created":"2021-02-11","cited_by_count":12,"area":null},{"id":"2301.10886","title":"Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning","created":"2023-01-26","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":"2311.13050","title":"Multi-fidelity Bayesian Optimization: A Review","created":"2023-11-21","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":"2112.14233","title":"Multitask Learning and Bandits via Robust Statistics","created":"2021-12-28","cited_by_count":11,"area":null},{"id":"2202.04718","title":"Designing Closed Human-in-the-loop Deferral Pipelines","created":"2022-02-09","cited_by_count":11,"area":null},{"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":"2206.02344","title":"Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets","created":"2022-06-06","cited_by_count":11,"area":null},{"id":"2209.07376","title":"Understanding Deep Neural Function Approximation in Reinforcement Learning via $\\epsilon$-Greedy Exploration","created":"2022-09-15","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":"2402.13399","title":"Learning and Sustaining Shared Normative Systems via Bayesian Rule Induction in Markov Games","created":"2024-02-20","cited_by_count":11,"area":null},{"id":"2409.02069","title":"A Deployed Online Reinforcement Learning Algorithm In An Oral Health Clinical Trial","created":"2024-09-03","cited_by_count":11,"area":null},{"id":"2511.18902","title":"VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL","created":"2025-11-24","cited_by_count":11,"area":"lr"},{"id":"2110.12175","title":"Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits","created":"2021-10-23","cited_by_count":10,"area":null},{"id":"2203.08248","title":"Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling","created":"2022-03-15","cited_by_count":10,"area":null},{"id":"2302.09339","title":"Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization","created":"2023-02-18","cited_by_count":10,"area":null},{"id":"2309.00591","title":"Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms","created":"2023-09-01","cited_by_count":10,"area":null},{"id":"2401.11665","title":"Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo","created":"2024-01-22","cited_by_count":10,"area":null},{"id":"2402.13754","title":"Reinforcement learning-assisted quantum architecture search for variational quantum algorithms","created":"2024-02-21","cited_by_count":10,"area":"deeprl"},{"id":"2406.05064","title":"Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning","created":"2024-06-07","cited_by_count":10,"area":"offlinerl"},{"id":"2603.15789","title":"Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learning","created":"2026-03-16","cited_by_count":10,"area":"deeprl"}],"next_cursor":"100"}