{"total":59,"rows":[{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120,"area":null},{"id":"2307.11046","title":"A Definition of Continual Reinforcement Learning","created":"2023-07-20","cited_by_count":101,"area":null},{"id":"2307.04345","title":"Continual Learning as Computationally Constrained Reinforcement Learning","created":"2023-07-10","cited_by_count":37,"area":null},{"id":"2212.10420","title":"Settling the Reward Hypothesis","created":"2022-12-20","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":"2107.09224","title":"From Predictions to Decisions: The Importance of Joint Predictive Distributions","created":"2021-07-20","cited_by_count":29,"area":null},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2110.04629","title":"The Neural Testbed: Evaluating Joint Predictions","created":"2021-10-09","cited_by_count":22,"area":null},{"id":"2211.01568","title":"Fine-Tuning Language Models via Epistemic Neural Networks","created":"2022-11-03","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":"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":"2108.10273","title":"Collect & Infer -- a fresh look at data-efficient Reinforcement Learning","created":"2021-08-23","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":"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":"2407.10583","title":"Three Dogmas of Reinforcement Learning","created":"2024-07-15","cited_by_count":14,"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":"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":"2505.10361","title":"Plasticity as the Mirror of Empowerment","created":"2025-05-15","cited_by_count":12,"area":null},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2211.01595","title":"Reinforcement Learning in Non-Markovian Environments","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2211.10282","title":"Exploring through Random Curiosity with General Value Functions","created":"2022-11-18","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":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","cited_by_count":10,"area":"deeprl"},{"id":"2505.21974","title":"BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL","created":"2025-05-28","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":"2409.15703","title":"Agent-state based policies in POMDPs: Beyond belief-state MDPs","created":"2024-09-24","cited_by_count":9,"area":"deeprl"},{"id":"2105.08769","title":"Learning and Information in Stochastic Networks and Queues","created":"2021-05-18","cited_by_count":8,"area":null},{"id":"2302.03561","title":"Optimizing Audio Recommendations for the Long-Term: A Reinforcement Learning Perspective","created":"2023-02-07","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":"2307.11044","title":"On the Convergence of Bounded Agents","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2203.00246","title":"An Information-Theoretic Framework for Supervised Learning","created":"2022-03-01","cited_by_count":6,"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":"2305.13747","title":"Optimizing Long-term Value for Auction-Based Recommender Systems via On-Policy Reinforcement Learning","created":"2023-05-23","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":"2407.06121","title":"Periodic agent-state based Q-learning for POMDPs","created":"2024-07-08","cited_by_count":6,"area":"deeprl"},{"id":"2201.01902","title":"Gaussian Imagination in Bandit Learning","created":"2022-01-06","cited_by_count":5,"area":null},{"id":"2211.03011","title":"On learning history based policies for controlling Markov decision processes","created":"2022-11-06","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2210.16872","title":"Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction","created":"2022-10-30","cited_by_count":4,"area":null},{"id":"2211.15931","title":"Posterior Sampling for Continuing Environments","created":"2022-11-29","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":"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":"2311.01990","title":"Conditions on Preference Relations that Guarantee the Existence of Optimal Policies","created":"2023-11-03","cited_by_count":3,"area":"alignment"},{"id":"2305.02093","title":"Efficient Online Decision Tree Learning with Active Feature Acquisition","created":"2023-05-03","cited_by_count":2,"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":"2512.01188","title":"Real-World Reinforcement Learning of Active Perception Behaviors","created":"2025-12-01","cited_by_count":1,"area":"deeprl"},{"id":"2212.01365","title":"An Information-Theoretic Analysis of Compute-Optimal Neural Scaling Laws","created":"2022-12-02","cited_by_count":0,"area":null},{"id":"2407.01456","title":"Information-Theoretic Foundations for Neural Scaling Laws","created":"2024-06-28","cited_by_count":0,"area":null},{"id":"2407.12178","title":"Exploration Unbound","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2605.02989","title":"Information Theory and Statistical Learning","created":"2026-05-04","cited_by_count":0,"area":"diffusion"},{"id":"2605.29405","title":"Information-Directed Offline-to-Online Reinforcement Learning","created":"2026-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2606.01072","title":"Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs","created":"2026-05-31","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}