{"total":67,"rows":[{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370,"area":"offlinerl"},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284,"area":"offlinerl"},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125,"area":"offlinerl"},{"id":"2206.13687","title":"POEM: Out-of-Distribution Detection with Posterior Sampling","created":"2022-06-28","cited_by_count":108,"area":null},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"area":null},{"id":"2404.11599","title":"Variational Bayesian Last Layers","created":"2024-04-17","cited_by_count":69,"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":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","cited_by_count":44,"area":"offlinerl"},{"id":"2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","created":"2023-05-29","cited_by_count":29,"area":null},{"id":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"area":null},{"id":"2106.03207","title":"Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage","created":"2021-06-06","cited_by_count":26,"area":"offlinerl"},{"id":"2106.04335","title":"Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization","created":"2021-06-08","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":"2106.03039","title":"Multi-facet Contextual Bandits: A Neural Network Perspective","created":"2021-06-06","cited_by_count":20,"area":null},{"id":"2105.14016","title":"Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model","created":"2021-05-28","cited_by_count":18,"area":null},{"id":"2310.16173","title":"On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\\epsilon$-Greedy Exploration","created":"2023-10-24","cited_by_count":17,"area":null},{"id":"2305.00477","title":"Posterior Sampling for Deep Reinforcement Learning","created":"2023-04-30","cited_by_count":16,"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":"2412.09477","title":"Bayesian Optimization via Continual Variational Last Layer Training","created":"2024-12-12","cited_by_count":13,"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":"2306.01460","title":"ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2303.05848","title":"Decision-Making Under Uncertainty: Beyond Probabilities","created":"2023-03-10","cited_by_count":9,"area":null},{"id":"2504.02515","title":"Exploration-Driven Generative Interactive Environments","created":"2025-04-03","cited_by_count":9,"area":"wm"},{"id":"2103.01932","title":"Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions","created":"2021-03-02","cited_by_count":8,"area":null},{"id":"2405.16030","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","created":"2024-05-25","cited_by_count":8,"area":"deeprl"},{"id":"2406.06946","title":"Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis","created":"2024-06-11","cited_by_count":8,"area":null},{"id":"2202.08867","title":"Fast online inference for nonlinear contextual bandit based on Generative Adversarial Network","created":"2022-02-17","cited_by_count":7,"area":null},{"id":"2404.19346","title":"Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning","created":"2024-04-30","cited_by_count":7,"area":"offlinerl"},{"id":"2102.03719","title":"State-Aware Variational Thompson Sampling for Deep Q-Networks","created":"2021-02-07","cited_by_count":5,"area":null},{"id":"2102.10085","title":"Output-Weighted Sampling for Multi-Armed Bandits with Extreme Payoffs","created":"2021-02-19","cited_by_count":5,"area":null},{"id":"2110.03155","title":"Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning","created":"2021-10-07","cited_by_count":5,"area":null},{"id":"2407.00801","title":"Model-Free Active Exploration in Reinforcement Learning","created":"2024-06-30","cited_by_count":5,"area":"deeprl"},{"id":"2606.00151","title":"Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying","created":"2026-05-29","cited_by_count":5,"area":"deeprl"},{"id":"2006.16498","title":"Accelerating Reinforcement Learning Agent with EEG-based Implicit Human Feedback","created":"2020-06-30","cited_by_count":4,"area":"alignment"},{"id":"2303.04012","title":"Exploration via Epistemic Value Estimation","created":"2023-03-07","cited_by_count":4,"area":null},{"id":"2507.13181","title":"Spectral Bellman Method: Unifying Representation and Exploration in RL","created":"2025-07-17","cited_by_count":4,"area":"deeprl"},{"id":"2109.07275","title":"DROMO: Distributionally Robust Offline Model-based Policy Optimization","created":"2021-09-15","cited_by_count":3,"area":"offlinerl"},{"id":"2110.13079","title":"Which Model to Trust: Assessing the Influence of Models on the Performance of Reinforcement Learning Algorithms for Continuous Control Tasks","created":"2021-10-25","cited_by_count":3,"area":null},{"id":"2205.13528","title":"SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning","created":"2022-05-26","cited_by_count":3,"area":null},{"id":"2503.20139","title":"Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learning","created":"2025-03-26","cited_by_count":3,"area":"deeprl"},{"id":"2602.19917","title":"Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning","created":"2026-02-23","cited_by_count":3,"area":"offlinerl"},{"id":"2106.11086","title":"Analytically Tractable Bayesian Deep Q-Learning","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2112.01575","title":"Towards Interactive Reinforcement Learning with Intrinsic Feedback","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2210.06168","title":"The Role of Exploration for Task Transfer in Reinforcement Learning","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2302.04250","title":"Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration","created":"2023-02-08","cited_by_count":2,"area":null},{"id":"2507.02639","title":"On Efficient Bayesian Exploration in Model-Based Reinforcement Learning","created":"2025-07-03","cited_by_count":2,"area":"deeprl"},{"id":"2202.08884","title":"BADDr: Bayes-Adaptive Deep Dropout RL for POMDPs","created":"2022-02-17","cited_by_count":1,"area":null},{"id":"2310.10818","title":"Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2312.13910","title":"Multi-Agent Probabilistic Ensembles with Trajectory Sampling for Connected Autonomous Vehicles","created":"2023-12-21","cited_by_count":1,"area":"driving"},{"id":"2409.05433","title":"State-Novelty Guided Action Persistence in Deep Reinforcement Learning","created":"2024-09-09","cited_by_count":1,"area":"deeprl"},{"id":"2503.18980","title":"CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning","created":"2025-03-23","cited_by_count":1,"area":"deeprl"},{"id":"2506.00917","title":"Q-learning with Posterior Sampling","created":"2025-06-01","cited_by_count":1,"area":"deeprl"},{"id":"2510.19531","title":"The Confusing Instance Principle for Online Linear Quadratic Control","created":"2025-10-22","cited_by_count":1,"area":"deeprl"},{"id":"2109.08518","title":"Knowledge is reward: Learning optimal exploration by predictive reward cashing","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2310.09338","title":"Uncertainty Quantification using Generative Approach","created":"2023-10-13","cited_by_count":0,"area":null},{"id":"2312.16142","title":"A Bayesian Framework of Deep Reinforcement Learning for Joint O-RAN/MEC Orchestration","created":"2023-12-26","cited_by_count":0,"area":null},{"id":"2404.00686","title":"Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning","created":"2024-03-31","cited_by_count":0,"area":"deeprl"},{"id":"2410.03119","title":"Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning Systems","created":"2024-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2501.09611","title":"EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learning","created":"2025-01-16","cited_by_count":0,"area":"deeprl"},{"id":"2508.21488","title":"Priors Matter: Addressing Misspecification in Bayesian Deep Q-Learning","created":"2025-08-29","cited_by_count":0,"area":"deeprl"},{"id":"2511.03836","title":"Enhancing Q-Value Updates in Deep Q-Learning via Successor-State Prediction","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2601.00737","title":"Stochastic Actor-Critic: Mitigating Overestimation via Temporal Aleatoric Uncertainty","created":"2026-01-02","cited_by_count":0,"area":"deeprl"},{"id":"2605.12084","title":"Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.04845","title":"Bayesian learning for the stochastic shortest path problem","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.17981","title":"Information-Based Exploration via Random Features for Reinforcement Learning","created":"2026-07-20","cited_by_count":0,"area":"deeprl"},{"id":"2608.03069","title":"Revisiting TD Target Aggregation under Uncertainty in Q-Learning","created":"2026-08-04","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}