{"total":25,"rows":[{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2211.05732","title":"The Sample Complexity of Online Contract Design","created":"2022-11-10","cited_by_count":35,"area":null},{"id":"2105.14989","title":"Representation Learning Beyond Linear Prediction Functions","created":"2021-05-31","cited_by_count":21,"area":null},{"id":"2211.11719","title":"First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains","created":"2022-11-21","cited_by_count":21,"area":null},{"id":"2104.06970","title":"Understanding the Eluder Dimension","created":"2021-04-14","cited_by_count":19,"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":"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":"2111.08911","title":"Fast Rates for Nonparametric Online Learning: From Realizability to Learning in Games","created":"2021-11-17","cited_by_count":16,"area":null},{"id":"2107.04518","title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2202.05448","title":"Fast Rates in Pool-Based Batch Active Learning","created":"2022-02-11","cited_by_count":15,"area":null},{"id":"2301.11518","title":"Online Learning in Stackelberg Games with an Omniscient Follower","created":"2023-01-27","cited_by_count":15,"area":null},{"id":"2205.15701","title":"Provable General Function Class Representation Learning in Multitask Bandits and MDPs","created":"2022-05-31","cited_by_count":12,"area":null},{"id":"2205.13450","title":"Variance-Aware Sparse Linear Bandits","created":"2022-05-26","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":"2107.06466","title":"Going Beyond Linear RL: Sample Efficient Neural Function Approximation","created":"2021-07-14","cited_by_count":9,"area":null},{"id":"2206.02326","title":"Asymptotic Instance-Optimal Algorithms for Interactive Decision Making","created":"2022-06-06","cited_by_count":7,"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":"2605.00751","title":"NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search","created":"2026-05-01","cited_by_count":5,"area":null},{"id":"2305.00322","title":"Toward $L_\\infty$-recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields","created":"2023-04-29","cited_by_count":4,"area":null},{"id":"2405.07331","title":"Stochastic Bandits with ReLU Neural Networks","created":"2024-05-12","cited_by_count":2,"area":null},{"id":"2503.03023","title":"Quantum Non-Linear Bandit Optimization","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2503.00387","title":"LNUCB-TA: Linear-nonlinear Hybrid Bandit Learning with Temporal Attention","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2306.06184","title":"A Unified Model and Dimension for Interactive Estimation","created":"2023-06-09","cited_by_count":0,"area":null},{"id":"2509.01924","title":"Non-Linear Model-Based Sequential Decision-Making in Agriculture","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2605.05791","title":"Fitted Q-Iteration with Continuous Actions and Adaptive Data: Smoothed Coverage and Minimax Rates","created":"2026-05-07","cited_by_count":0,"area":null}],"next_cursor":null}