{"list":"other","total":55,"rows":[{"id":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"2002.06673","title":"Performative Prediction","created":"2020-02-16","cited_by_count":327},{"id":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"id":"1506.06980","title":"Strategic Classification","created":"2015-06-23","cited_by_count":257},{"id":"1901.00137","title":"A Theoretical Analysis of Deep Q-Learning","created":"2019-01-01","cited_by_count":215},{"id":"1710.07887","title":"Strategic Classification from Revealed Preferences","created":"2017-10-22","cited_by_count":128},{"id":"1906.03804","title":"Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal","created":"2019-06-10","cited_by_count":127},{"id":"2002.09516","title":"Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation","created":"2020-02-21","cited_by_count":120},{"id":"2110.14555","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","created":"2021-10-27","cited_by_count":114},{"id":"1808.08460","title":"The Social Cost of Strategic Classification","created":"2018-08-25","cited_by_count":105},{"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":"2102.08570","title":"Outside the Echo Chamber: Optimizing the Performative Risk","created":"2021-02-17","cited_by_count":96},{"id":"2009.10982","title":"An Introduction to Proximal Causal Learning","created":"2020-09-23","cited_by_count":95},{"id":"2006.06887","title":"Stochastic Optimization for Performative Prediction","created":"2020-06-12","cited_by_count":93},{"id":"1910.10362","title":"Strategic Classification is Causal Modeling in Disguise","created":"2019-10-23","cited_by_count":92},{"id":"2011.03885","title":"Performative Prediction in a Stateful World","created":"2020-11-08","cited_by_count":90},{"id":"2006.07201","title":"Minimax Estimation of Conditional Moment Models","created":"2020-06-12","cited_by_count":83},{"id":"1808.08646","title":"The Disparate Effects of Strategic Manipulation","created":"2018-08-27","cited_by_count":75},{"id":"1712.00579","title":"Online Reinforcement Learning in Stochastic Games","created":"2017-12-02","cited_by_count":67},{"id":"2110.04184","title":"When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?","created":"2021-10-08","cited_by_count":67},{"id":"1909.03739","title":"Off-Policy Evaluation in Partially Observable Environments","created":"2019-09-09","cited_by_count":66},{"id":"2102.11592","title":"Strategic Classification in the Dark","created":"2021-02-23","cited_by_count":66},{"id":"2002.10066","title":"Causal Strategic Linear Regression","created":"2020-02-24","cited_by_count":65},{"id":"2003.05623","title":"Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding","created":"2020-03-12","cited_by_count":61},{"id":"2103.01826","title":"Strategic Classification Made Practical","created":"2021-03-02","cited_by_count":59},{"id":"2106.02748","title":"Decentralized Q-Learning in Zero-sum Markov Games","created":"2021-06-04","cited_by_count":58},{"id":"2106.12529","title":"Who Leads and Who Follows in Strategic Classification?","created":"2021-06-23","cited_by_count":53},{"id":"2008.01710","title":"The Strategic Perceptron","created":"2020-08-04","cited_by_count":48},{"id":"2201.03398","title":"Multiplayer Performative Prediction: Learning in Decision-Dependent Games","created":"2022-01-10","cited_by_count":44},{"id":"2202.07511","title":"Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets","created":"2022-02-15","cited_by_count":44},{"id":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42},{"id":"2007.13893","title":"Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders","created":"2020-07-27","cited_by_count":41},{"id":"2006.12311","title":"Provably Efficient Causal Reinforcement Learning with Confounded Observational Data","created":"2020-06-22","cited_by_count":40},{"id":"2202.00628","title":"Regret Minimization with Performative Feedback","created":"2022-02-01","cited_by_count":40},{"id":"2110.00800","title":"State Dependent Performative Prediction with Stochastic Approximation","created":"2021-10-02","cited_by_count":39},{"id":"2110.05707","title":"On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning","created":"2021-10-12","cited_by_count":36},{"id":"2201.06169","title":"On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation","created":"2022-01-17","cited_by_count":33},{"id":"2106.03827","title":"Stateful Strategic Regression","created":"2021-06-07","cited_by_count":32},{"id":"2201.03522","title":"When is Offline Two-Player Zero-Sum Markov Game Solvable?","created":"2022-01-10","cited_by_count":28},{"id":"2110.12343","title":"Off-Policy Evaluation in Partially Observed Markov Decision Processes under Sequential Ignorability","created":"2021-10-24","cited_by_count":24},{"id":"2112.13521","title":"Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers?","created":"2021-12-27","cited_by_count":24},{"id":"2105.10148","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","created":"2021-05-21","cited_by_count":22},{"id":"2109.08240","title":"Strategic Ranking","created":"2021-09-16","cited_by_count":21},{"id":"1606.08718","title":"Learning Nash Equilibrium for General-Sum Markov Games from Batch Data","created":"2016-06-28","cited_by_count":20},{"id":"2203.06803","title":"Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits","created":"2022-03-14","cited_by_count":17},{"id":"2002.07024","title":"Gaming Helps! Learning from Strategic Interactions in Natural Dynamics","created":"2020-02-17","cited_by_count":15},{"id":"2111.00781","title":"Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure","created":"2021-11-01","cited_by_count":14},{"id":"2104.07822","title":"Estimating and Improving Dynamic Treatment Regimes With a Time-Varying Instrumental Variable","created":"2021-04-15","cited_by_count":13},{"id":"2206.01588","title":"Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games","created":"2022-06-03","cited_by_count":12},{"id":"2206.04044","title":"Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games","created":"2022-06-08","cited_by_count":11},{"id":"2102.07663","title":"Causal Markov Decision Processes: Learning Good Interventions Efficiently","created":"2021-02-15","cited_by_count":7},{"id":"1309.7824","title":"Linear Regression from Strategic Data Sources","created":"2013-09-30","cited_by_count":6},{"id":"2107.10093","title":"Incentivizing Compliance with Algorithmic Instruments","created":"2021-07-21","cited_by_count":4},{"id":"2206.08542","title":"Strategic Representation","created":"2022-06-17","cited_by_count":4}],"next_cursor":null}