{"list":"other","total":57,"rows":[{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"1610.09512","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","created":"2016-10-29","cited_by_count":292},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"id":"1806.02450","title":"A Finite Time Analysis of Temporal Difference Learning With Linear Function Approximation","created":"2018-06-06","cited_by_count":229},{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223},{"id":"1901.00137","title":"A Theoretical Analysis of Deep Q-Learning","created":"2019-01-01","cited_by_count":215},{"id":"2003.00153","title":"Learning Near Optimal Policies with Low Inherent Bellman Error","created":"2020-02-29","cited_by_count":181},{"id":"1810.08033","title":"Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality","created":"2018-10-18","cited_by_count":162},{"id":"1703.08862","title":"Socially Aware Motion Planning with Deep Reinforcement Learning","created":"2017-03-26","cited_by_count":136},{"id":"1707.04926","title":"Theoretical insights into the optimization landscape of over-parameterized shallow neural networks","created":"2017-07-16","cited_by_count":128},{"id":"2002.09516","title":"Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation","created":"2020-02-21","cited_by_count":120},{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119},{"id":"2005.10190","title":"Feature Purification: How Adversarial Training Performs Robust Deep Learning","created":"2020-05-20","cited_by_count":107},{"id":"1712.08968","title":"Spurious Local Minima are Common in Two-Layer ReLU Neural Networks","created":"2017-12-24","cited_by_count":104},{"id":"2006.13165","title":"Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping","created":"2020-06-23","cited_by_count":102},{"id":"1910.10597","title":"Sample Complexity of Reinforcement Learning using Linearly Combined Model Ensembles","created":"2019-10-23","cited_by_count":100},{"id":"2006.03041","title":"Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction","created":"2020-06-04","cited_by_count":95},{"id":"1706.03175","title":"Recovery Guarantees for One-hidden-layer Neural Networks","created":"2017-06-10","cited_by_count":94},{"id":"1902.02234","title":"Finite-Sample Analysis for SARSA with Linear Function Approximation","created":"2019-02-06","cited_by_count":85},{"id":"1711.00501","title":"Learning One-hidden-layer Neural Networks with Landscape Design","created":"2017-11-01","cited_by_count":81},{"id":"1710.10174","title":"SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data","created":"2017-10-27","cited_by_count":79},{"id":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77},{"id":"1802.04412","title":"Efficient Exploration through Bayesian Deep Q-Networks","created":"2018-02-13","cited_by_count":67},{"id":"1702.07966","title":"Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs","created":"2017-02-26","cited_by_count":61},{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49},{"id":"2206.01717","title":"A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features","created":"2022-06-03","cited_by_count":49},{"id":"1912.04511","title":"A Finite-Time Analysis of Q-Learning with Neural Network Function Approximation","created":"2019-12-10","cited_by_count":47},{"id":"1907.09059","title":"Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges","created":"2019-07-22","cited_by_count":37},{"id":"2306.04073","title":"Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks","created":"2023-06-07","cited_by_count":35},{"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},{"id":"1811.01885","title":"Learning Two Layer Rectified Neural Networks in Polynomial Time","created":"2018-11-05","cited_by_count":31},{"id":"2206.09421","title":"Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation","created":"2022-06-19","cited_by_count":31},{"id":"2111.13807","title":"Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization","created":"2021-11-27","cited_by_count":25},{"id":"2006.14117","title":"Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case","created":"2020-06-25","cited_by_count":24},{"id":"2207.03584","title":"Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling","created":"2022-07-07","cited_by_count":23},{"id":"1808.04685","title":"Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization","created":"2018-08-14","cited_by_count":21},{"id":"1909.02506","title":"$\\sqrt{n}$-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank","created":"2019-09-05","cited_by_count":20},{"id":"2201.08514","title":"How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis","created":"2022-01-21","cited_by_count":19},{"id":"1510.03528","title":"$\\ell_1$-regularized Neural Networks are Improperly Learnable in Polynomial Time","created":"2015-10-13","cited_by_count":16},{"id":"2302.02922","title":"Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks","created":"2023-02-06","cited_by_count":16},{"id":"2110.05667","title":"Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks","created":"2021-10-12","cited_by_count":14},{"id":"2206.02887","title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks","created":"2022-06-06","cited_by_count":12},{"id":"2209.07376","title":"Understanding Deep Neural Function Approximation in Reinforcement Learning via $\\epsilon$-Greedy Exploration","created":"2022-09-15","cited_by_count":11},{"id":"1804.10328","title":"Scalable Bilinear $\\pi$ Learning Using State and Action Features","created":"2018-04-27","cited_by_count":10},{"id":"1405.3229","title":"Rate of Convergence and Error Bounds for LSTD($\\lambda$)","created":"2014-05-13","cited_by_count":8},{"id":"2103.06671","title":"Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks","created":"2021-03-11","cited_by_count":8},{"id":"2309.13291","title":"Reinforcement Learning for Robust Header Compression under Model Uncertainty","created":"2023-09-23","cited_by_count":1}],"next_cursor":null}