{"list":"other","total":51,"rows":[{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1807.03765","title":"Is Q-learning Provably Efficient?","created":"2018-07-10","cited_by_count":487},{"id":"1605.02065","title":"Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds","created":"2016-05-06","cited_by_count":346},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"2006.01107","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","created":"2020-06-01","cited_by_count":234},{"id":"1703.07710","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","created":"2017-03-22","cited_by_count":176},{"id":"2103.00039","title":"Practical and Private (Deep) Learning without Sampling or Shuffling","created":"2021-02-26","cited_by_count":170},{"id":"2110.14555","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","created":"2021-10-27","cited_by_count":114},{"id":"2002.04017","title":"Provable Self-Play Algorithms for Competitive Reinforcement Learning","created":"2020-02-10","cited_by_count":113},{"id":"2006.12007","title":"Near-Optimal Reinforcement Learning with Self-Play","created":"2020-06-22","cited_by_count":109},{"id":"2010.01604","title":"A Sharp Analysis of Model-based Reinforcement Learning with Self-Play","created":"2020-10-04","cited_by_count":105},{"id":"2012.06421","title":"When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?","created":"2020-12-11","cited_by_count":104},{"id":"2002.07066","title":"Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium","created":"2020-02-17","cited_by_count":100},{"id":"1810.00068","title":"Differentially Private Contextual Linear Bandits","created":"2018-09-28","cited_by_count":82},{"id":"2011.12692","title":"Towards Playing Full MOBA Games with Deep Reinforcement Learning","created":"2020-11-25","cited_by_count":78},{"id":"2009.09052","title":"Private Reinforcement Learning with PAC and Regret Guarantees","created":"2020-09-18","cited_by_count":51},{"id":"2110.05707","title":"On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning","created":"2021-10-12","cited_by_count":36},{"id":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32},{"id":"1901.10634","title":"Privacy-preserving Q-Learning with Functional Noise in Continuous State Spaces","created":"2019-01-30","cited_by_count":30},{"id":"2302.06606","title":"Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation","created":"2023-02-13","cited_by_count":30},{"id":"2302.03673","title":"Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation","created":"2023-02-07","cited_by_count":27},{"id":"1311.2828","title":"Private Matchings and Allocations","created":"2013-11-12","cited_by_count":23},{"id":"2112.10599","title":"Differentially Private Regret Minimization in Episodic Markov Decision Processes","created":"2021-12-20","cited_by_count":23},{"id":"2010.07778","title":"Local Differential Privacy for Regret Minimization in Reinforcement Learning","created":"2020-10-15","cited_by_count":22},{"id":"2201.07052","title":"Differentially Private Reinforcement Learning with Linear Function Approximation","created":"2022-01-18","cited_by_count":22},{"id":"2206.00810","title":"Offline Reinforcement Learning with Differential Privacy","created":"2022-06-02","cited_by_count":20},{"id":"1603.02010","title":"Differentially Private Policy Evaluation","created":"2016-03-07","cited_by_count":19},{"id":"2310.16960","title":"Privately Aligning Language Models with Reinforcement Learning","created":"2023-10-25","cited_by_count":17},{"id":"2212.04680","title":"Near-Optimal Differentially Private Reinforcement Learning","created":"2022-12-09","cited_by_count":16},{"id":"2010.10380","title":"Negotiating Team Formation Using Deep Reinforcement Learning","created":"2020-10-20","cited_by_count":13},{"id":"2110.10133","title":"Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes","created":"2021-10-19","cited_by_count":13},{"id":"2210.00701","title":"Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation","created":"2022-10-03","cited_by_count":13},{"id":"2310.19733","title":"Differentially Private Reward Estimation with Preference Feedback","created":"2023-10-30","cited_by_count":12},{"id":"2112.01585","title":"Differentially Private Exploration in Reinforcement Learning with Linear Representation","created":"2021-12-02","cited_by_count":11},{"id":"2205.09873","title":"Differentially Private Linear Sketches: Efficient Implementations and Applications","created":"2022-05-19","cited_by_count":10},{"id":"2001.11718","title":"Locally Private Distributed Reinforcement Learning","created":"2020-01-31","cited_by_count":9},{"id":"2302.12456","title":"Logarithmic Switching Cost in Reinforcement Learning beyond Linear MDPs","created":"2023-02-24","cited_by_count":9},{"id":"2202.01292","title":"Improved Regret for Differentially Private Exploration in Linear MDP","created":"2022-02-02","cited_by_count":8},{"id":"2310.12523","title":"Privacy Preserving Large Language Models: ChatGPT Case Study Based Vision and Framework","created":"2023-10-19","cited_by_count":8},{"id":"2108.11563","title":"Adaptive Control of Differentially Private Linear Quadratic Systems","created":"2021-08-26","cited_by_count":7},{"id":"2201.10447","title":"Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization","created":"2022-01-25","cited_by_count":7},{"id":"2012.15019","title":"Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients","created":"2020-12-30","cited_by_count":6},{"id":"1910.05876","title":"Actor Critic with Differentially Private Critic","created":"2019-10-14","cited_by_count":5},{"id":"2306.01121","title":"Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards","created":"2023-06-01","cited_by_count":4},{"id":"1902.00174","title":"Privacy Preserving Off-Policy Evaluation","created":"2019-02-01","cited_by_count":3},{"id":"2307.00268","title":"Hiding in Plain Sight: Differential Privacy Noise Exploitation for Evasion-resilient Localized Poisoning Attacks in Multiagent Reinforcement Learning","created":"2023-07-01","cited_by_count":2},{"id":"2308.01274","title":"BRNES: Enabling Security and Privacy-aware Experience Sharing in Multiagent Robotic and Autonomous Systems","created":"2023-08-02","cited_by_count":1},{"id":"2308.09902","title":"DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning","created":"2023-08-19","cited_by_count":1},{"id":"2311.06255","title":"Privacy-Engineered Value Decomposition Networks for Cooperative Multi-Agent Reinforcement Learning","created":"2023-09-13","cited_by_count":1}],"next_cursor":null}