{"total":59,"rows":[{"id":"2103.10897","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","created":"2021-03-19","cited_by_count":178,"area":null},{"id":"2107.04050","title":"Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning","created":"2021-07-08","cited_by_count":38,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"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":"2306.12371","title":"Optimistic Active Exploration of Dynamical Systems","created":"2023-06-21","cited_by_count":32,"area":null},{"id":"2209.15634","title":"A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning","created":"2022-09-30","cited_by_count":31,"area":null},{"id":"2102.05800","title":"Robust Policy Gradient against Strong Data Corruption","created":"2021-02-11","cited_by_count":30,"area":null},{"id":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2202.08311","title":"Single Trajectory Nonparametric Learning of Nonlinear Dynamics","created":"2022-02-16","cited_by_count":26,"area":null},{"id":"2110.06418","title":"Stabilizing Dynamical Systems via Policy Gradient Methods","created":"2021-10-13","cited_by_count":25,"area":null},{"id":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24,"area":null},{"id":"2106.06098","title":"Meta-Adaptive Nonlinear Control: Theory and Algorithms","created":"2021-06-11","cited_by_count":23,"area":null},{"id":"2310.19848","title":"Efficient Exploration in Continuous-time Model-based Reinforcement Learning","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2110.09771","title":"On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game","created":"2021-10-19","cited_by_count":20,"area":null},{"id":"2303.10506","title":"Neural Operators of Backstepping Controller and Observer Gain Functions for Reaction-Diffusion PDEs","created":"2023-03-18","cited_by_count":18,"area":null},{"id":"2306.09210","title":"Optimal Exploration for Model-Based RL in Nonlinear Systems","created":"2023-06-15","cited_by_count":18,"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":"2204.09787","title":"Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency","created":"2022-04-20","cited_by_count":16,"area":null},{"id":"2102.05214","title":"Task-Optimal Exploration in Linear Dynamical Systems","created":"2021-02-10","cited_by_count":15,"area":null},{"id":"2201.11211","title":"Learning Mixtures of Linear Dynamical Systems","created":"2022-01-26","cited_by_count":15,"area":null},{"id":"2107.07410","title":"PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration","created":"2021-07-15","cited_by_count":14,"area":null},{"id":"2210.08349","title":"When to Update Your Model: Constrained Model-based Reinforcement Learning","created":"2022-10-15","cited_by_count":14,"area":null},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2202.07890","title":"Online Control of Unknown Time-Varying Dynamical Systems","created":"2022-02-16","cited_by_count":13,"area":null},{"id":"2303.00694","title":"The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms","created":"2023-03-01","cited_by_count":12,"area":null},{"id":"2205.14035","title":"Learning to Control Linear Systems can be Hard","created":"2022-05-27","cited_by_count":11,"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":"2110.06150","title":"Sparsity in Partially Controllable Linear Systems","created":"2021-10-12","cited_by_count":9,"area":null},{"id":"2302.00727","title":"Sample Complexity of Kernel-Based Q-Learning","created":"2023-02-01","cited_by_count":8,"area":null},{"id":"2403.12732","title":"Tighter Confidence Bounds for Sequential Kernel Regression","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2110.07807","title":"Provable Regret Bounds for Deep Online Learning and Control","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2401.00073","title":"Nonasymptotic Regret Analysis of Adaptive Linear Quadratic Control with Model Misspecification","created":"2023-12-29","cited_by_count":6,"area":null},{"id":"2106.15775","title":"Koopman Spectrum Nonlinear Regulators and Efficient Online Learning","created":"2021-06-30","cited_by_count":5,"area":null},{"id":"2108.02307","title":"Regret Analysis of Learning-Based MPC with Partially-Unknown Cost Function","created":"2021-08-04","cited_by_count":5,"area":null},{"id":"2112.14195","title":"Exponential Family Model-Based Reinforcement Learning via Score Matching","created":"2021-12-28","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":"2206.01704","title":"KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systems","created":"2022-06-03","cited_by_count":5,"area":null},{"id":"2302.05430","title":"Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making","created":"2023-02-10","cited_by_count":5,"area":null},{"id":"2107.07732","title":"Robust Online Control with Model Misspecification","created":"2021-07-16","cited_by_count":4,"area":null},{"id":"2207.14419","title":"Sample-efficient Safe Learning for Online Nonlinear Control with Control Barrier Functions","created":"2022-07-29","cited_by_count":3,"area":null},{"id":"2212.06251","title":"Autoregressive Bandits","created":"2022-12-12","cited_by_count":3,"area":null},{"id":"2304.03907","title":"Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding","created":"2023-04-08","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":"2601.09825","title":"Eluder dimension: localise it!","created":"2026-01-14","cited_by_count":3,"area":null},{"id":"2206.00270","title":"Provably Efficient Lifelong Reinforcement Learning with Linear Function Approximation","created":"2022-06-01","cited_by_count":2,"area":null},{"id":"2510.01620","title":"Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2107.05849","title":"Model Selection for Generic Reinforcement Learning","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2207.02992","title":"Model Selection in Reinforcement Learning with General Function Approximations","created":"2022-07-06","cited_by_count":1,"area":null},{"id":"2307.05834","title":"Scaling Distributed Multi-task Reinforcement Learning with Experience Sharing","created":"2023-07-11","cited_by_count":1,"area":null},{"id":"2402.06614","title":"The Complexity of Sequential Prediction in Dynamical Systems","created":"2024-02-09","cited_by_count":1,"area":null},{"id":"2406.18805","title":"Online Stackelberg Optimization via Nonlinear Control","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2509.16650","title":"Safe and Near-Optimal Control with Online Dynamics Learning","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2202.05799","title":"Rate-matching the regret lower-bound in the linear quadratic regulator with unknown dynamics","created":"2022-02-11","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":"2206.02507","title":"Learning to Control under Time-Varying Environment","created":"2022-06-06","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":"2311.12230","title":"Data-Guided Regulator for Adaptive Nonlinear Control","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2501.10261","title":"Logarithmic Regret for Nonlinear Control","created":"2025-01-17","cited_by_count":0,"area":null},{"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}