{"total":86,"rows":[{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164,"area":"offlinerl"},{"id":"2110.04652","title":"Representation Learning for Online and Offline RL in Low-rank MDPs","created":"2021-10-09","cited_by_count":129,"area":"offlinerl"},{"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":"2201.09802","title":"Constrained Policy Optimization via Bayesian World Models","created":"2022-01-24","cited_by_count":57,"area":"wm"},{"id":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","cited_by_count":44,"area":"offlinerl"},{"id":"2107.04050","title":"Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning","created":"2021-07-08","cited_by_count":38,"area":null},{"id":"2306.12371","title":"Optimistic Active Exploration of Dynamical Systems","created":"2023-06-21","cited_by_count":32,"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":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"area":null},{"id":"2211.10257","title":"Model-based Causal Bayesian Optimization","created":"2022-11-18","cited_by_count":26,"area":null},{"id":"2410.09486","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","created":"2024-10-12","cited_by_count":23,"area":"deeprl"},{"id":"2310.19848","title":"Efficient Exploration in Continuous-time Model-based Reinforcement Learning","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2211.02222","title":"The Benefits of Model-Based Generalization in Reinforcement Learning","created":"2022-11-04","cited_by_count":17,"area":null},{"id":"2309.02236","title":"Distributionally Robust Model-based Reinforcement Learning with Large State Spaces","created":"2023-09-05","cited_by_count":17,"area":null},{"id":"2402.05367","title":"Principled Preferential Bayesian Optimization","created":"2024-02-08","cited_by_count":16,"area":null},{"id":"2302.12526","title":"Model-Based Uncertainty in Value Functions","created":"2023-02-24","cited_by_count":15,"area":null},{"id":"2103.10369","title":"Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning","created":"2021-03-18","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":"2303.01076","title":"Hallucinated Adversarial Control for Conservative Offline Policy Evaluation","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2402.08991","title":"Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption","created":"2024-02-14","cited_by_count":12,"area":"deeprl"},{"id":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2104.11706","title":"Safe Chance Constrained Reinforcement Learning for Batch Process Control","created":"2021-04-23","cited_by_count":11,"area":null},{"id":"2107.11587","title":"Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?","created":"2021-07-24","cited_by_count":11,"area":null},{"id":"2406.01163","title":"When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL","created":"2024-06-03","cited_by_count":9,"area":"deeprl"},{"id":"2105.12991","title":"Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization","created":"2021-05-27","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":"2403.10929","title":"Function-space Parameterization of Neural Networks for Sequential Learning","created":"2024-03-16","cited_by_count":8,"area":null},{"id":"2403.16644","title":"Bridging the Sim-to-Real Gap with Bayesian Inference","created":"2024-03-25","cited_by_count":8,"area":null},{"id":"2204.04558","title":"Gradient-Based Trajectory Optimization With Learned Dynamics","created":"2022-04-09","cited_by_count":7,"area":null},{"id":"2311.08376","title":"Ensemble sampling for linear bandits: small ensembles suffice","created":"2023-11-14","cited_by_count":7,"area":null},{"id":"2511.00423","title":"Bootstrap Off-policy with World Model","created":"2025-11-01","cited_by_count":7,"area":"wm"},{"id":"2511.20066","title":"SOMBRL: Scalable and Optimistic Model-Based RL","created":"2025-11-25","cited_by_count":7,"area":"deeprl"},{"id":"2110.07985","title":"On-Policy Model Errors in Reinforcement Learning","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2207.01337","title":"Safe Reinforcement Learning via Confidence-Based Filters","created":"2022-07-04","cited_by_count":6,"area":null},{"id":"2305.20011","title":"Constrained Causal Bayesian Optimization","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2309.12671","title":"How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2311.07558","title":"Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2502.06645","title":"Koopman-Equivariant Gaussian Processes","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2601.19612","title":"Safe Exploration via Policy Priors","created":"2026-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2106.15775","title":"Koopman Spectrum Nonlinear Regulators and Efficient Online Learning","created":"2021-06-30","cited_by_count":5,"area":null},{"id":"2202.00602","title":"Meta-Learning Hypothesis Spaces for Sequential Decision-making","created":"2022-02-01","cited_by_count":5,"area":null},{"id":"2209.07676","title":"Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning","created":"2022-09-16","cited_by_count":5,"area":null},{"id":"2301.11426","title":"Model-based Offline Reinforcement Learning with Local Misspecification","created":"2023-01-26","cited_by_count":5,"area":"offlinerl"},{"id":"2308.06590","title":"Value-Distributional Model-Based Reinforcement Learning","created":"2023-08-12","cited_by_count":5,"area":null},{"id":"2502.19859","title":"IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic","created":"2025-02-27","cited_by_count":5,"area":"offlinerl"},{"id":"2510.08962","title":"Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation","created":"2025-10-10","cited_by_count":5,"area":null},{"id":"2303.04012","title":"Exploration via Epistemic Value Estimation","created":"2023-03-07","cited_by_count":4,"area":null},{"id":"2306.17052","title":"Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning","created":"2023-06-29","cited_by_count":4,"area":null},{"id":"2307.16625","title":"Adversarial Causal Bayesian Optimization","created":"2023-07-31","cited_by_count":4,"area":null},{"id":"2402.03055","title":"Deep Exploration with PAC-Bayes","created":"2024-02-05","cited_by_count":4,"area":"deeprl"},{"id":"2405.05890","title":"Safe Exploration Using Bayesian World Models and Log-Barrier Optimization","created":"2024-05-09","cited_by_count":4,"area":"wm"},{"id":"2406.01175","title":"NeoRL: Efficient Exploration for Nonepisodic RL","created":"2024-06-03","cited_by_count":4,"area":"deeprl"},{"id":"2503.17678","title":"Computationally and Sample Efficient Safe Reinforcement Learning Using Adaptive Conformal Prediction","created":"2025-03-22","cited_by_count":4,"area":"deeprl"},{"id":"2510.20725","title":"No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes","created":"2025-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2309.05582","title":"Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning","created":"2023-09-11","cited_by_count":3,"area":null},{"id":"2312.04386","title":"Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2402.02277","title":"Causal Bayesian Optimization via Exogenous Distribution Learning","created":"2024-02-03","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":"2510.24482","title":"Sample-efficient and Scalable Exploration in Continuous-Time RL","created":"2025-10-28","cited_by_count":3,"area":"deeprl"},{"id":"2511.05355","title":"SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning","created":"2025-11-07","cited_by_count":3,"area":null},{"id":"2302.01491","title":"DiSProD: Differentiable Symbolic Propagation of Distributions for Planning","created":"2023-02-03","cited_by_count":2,"area":null},{"id":"2510.27428","title":"Learning Soft Robotic Dynamics with Active Exploration","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2603.08287","title":"Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces","created":"2026-03-09","cited_by_count":2,"area":"deeprl"},{"id":"2207.14443","title":"A Survey of Learning on Small Data: Generalization, Optimization, and Challenge","created":"2022-07-29","cited_by_count":1,"area":null},{"id":"2504.08604","title":"Neural Fidelity Calibration for Informative Sim-to-Real Adaptation","created":"2025-04-11","cited_by_count":1,"area":"diffusion"},{"id":"2509.16650","title":"Safe and Near-Optimal Control with Online Dynamics Learning","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2510.19531","title":"The Confusing Instance Principle for Online Linear Quadratic Control","created":"2025-10-22","cited_by_count":1,"area":"deeprl"},{"id":"2601.10905","title":"Action Shapley: A Training Data Selection Metric for World Model in Reinforcement Learning","created":"2026-01-15","cited_by_count":1,"area":"wm"},{"id":"2603.28938","title":"Optimistic Online LQR via Intrinsic Rewards","created":"2026-03-30","cited_by_count":1,"area":"deeprl"},{"id":"2604.02260","title":"Model-Based Reinforcement Learning for Control under Time-Varying Dynamics","created":"2026-04-02","cited_by_count":1,"area":"deeprl"},{"id":"2202.07301","title":"User-Oriented Robust Reinforcement Learning","created":"2022-02-15","cited_by_count":0,"area":null},{"id":"2206.00861","title":"Dynamic Structure Estimation from Bandit Feedback using Nonvanishing Exponential Sums","created":"2022-06-02","cited_by_count":0,"area":null},{"id":"2301.03142","title":"Exploration in Model-based Reinforcement Learning with Randomized Reward","created":"2023-01-09","cited_by_count":0,"area":null},{"id":"2307.04415","title":"Episodic Gaussian Process-Based Learning Control with Vanishing Tracking Errors","created":"2023-07-10","cited_by_count":0,"area":null},{"id":"2312.17411","title":"Generative Posterior Networks for Approximately Bayesian Epistemic Uncertainty Estimation","created":"2023-12-29","cited_by_count":0,"area":null},{"id":"2403.17233","title":"Active Learning of Dynamics Using Prior Domain Knowledge in the Sampling Process","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2405.12001","title":"Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning","created":"2024-05-20","cited_by_count":0,"area":null},{"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":"2509.05732","title":"Simulation Priors for Data-Efficient Deep Learning","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2604.14243","title":"Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.09757","title":"On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.19469","title":"Sampling-Based Safe Reinforcement Learning","created":"2026-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2606.19328","title":"UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning","created":"2026-06-17","cited_by_count":0,"area":"alignment"},{"id":"2607.16501","title":"Certifiable Safe Model-Based Reinforcement Learning with Control-Affine Dynamics Approximation","created":"2026-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2609.35525","title":"Deep Epistemic Value Functions for Optimistic Exploration","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2610.16149","title":"Equilibrium Learning in Unbounded Stochastic Games with Gaussian Transitions","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}