{"list":"other","total":74,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1705.10467","title":"Federated Multi-Task Learning","created":"2017-05-30","cited_by_count":672},{"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":"2002.05516","title":"Federated Learning of a Mixture of Global and Local Models","created":"2020-02-10","cited_by_count":210},{"id":"1901.00210","title":"Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds","created":"2019-01-01","cited_by_count":195},{"id":"1906.03804","title":"Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal","created":"2019-06-10","cited_by_count":127},{"id":"2004.10019","title":"Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition","created":"2020-04-21","cited_by_count":127},{"id":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124},{"id":"2010.03531","title":"Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited","created":"2020-10-07","cited_by_count":106},{"id":"1905.03814","title":"Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs","created":"2019-05-09","cited_by_count":105},{"id":"2009.13503","title":"Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon","created":"2020-09-28","cited_by_count":99},{"id":"1904.01763","title":"Batched Multi-armed Bandits Problem","created":"2019-04-03","cited_by_count":98},{"id":"2102.06548","title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","created":"2021-02-12","cited_by_count":92},{"id":"1706.04972","title":"Device Placement Optimization with Reinforcement Learning","created":"2017-06-13","cited_by_count":86},{"id":"1811.03056","title":"Policy Certificates: Towards Accountable Reinforcement Learning","created":"2018-11-07","cited_by_count":81},{"id":"2011.11566","title":"Logarithmic Regret for Reinforcement Learning with Linear Function Approximation","created":"2020-11-23","cited_by_count":79},{"id":"1905.12849","title":"Provably Efficient Q-Learning with Low Switching Cost","created":"2019-05-30","cited_by_count":78},{"id":"2204.02634","title":"Federated Reinforcement Learning with Environment Heterogeneity","created":"2022-04-06","cited_by_count":63},{"id":"2006.09118","title":"$Q$-learning with Logarithmic Regret","created":"2020-06-16","cited_by_count":60},{"id":"2110.14074","title":"Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee","created":"2021-10-26","cited_by_count":54},{"id":"2110.04645","title":"Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning","created":"2021-10-09","cited_by_count":53},{"id":"2102.04692","title":"Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap","created":"2021-02-09","cited_by_count":49},{"id":"2103.01312","title":"UCB Momentum Q-learning: Correcting the bias without forgetting","created":"2021-03-01","cited_by_count":46},{"id":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45},{"id":"2108.02717","title":"Beyond No Regret: Instance-Dependent PAC Reinforcement Learning","created":"2021-08-05","cited_by_count":41},{"id":"1801.04405","title":"A Survey on Compiler Autotuning using Machine Learning","created":"2018-01-13","cited_by_count":40},{"id":"2112.03432","title":"First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach","created":"2021-12-07","cited_by_count":38},{"id":"2305.10697","title":"The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond","created":"2023-05-18","cited_by_count":36},{"id":"1806.00775","title":"Exploration in Structured Reinforcement Learning","created":"2018-06-03","cited_by_count":34},{"id":"2006.05879","title":"Planning in Markov Decision Processes with Gap-Dependent Sample Complexity","created":"2020-06-10","cited_by_count":34},{"id":"2107.01264","title":"Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning","created":"2021-07-02","cited_by_count":34},{"id":"2207.02575","title":"Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design","created":"2022-07-06","cited_by_count":33},{"id":"1808.03196","title":"Learning to Optimize Join Queries With Deep Reinforcement Learning","created":"2018-08-09","cited_by_count":32},{"id":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32},{"id":"2401.15273","title":"Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning","created":"2024-01-27","cited_by_count":31},{"id":"2106.02847","title":"Navigating to the Best Policy in Markov Decision Processes","created":"2021-06-05","cited_by_count":29},{"id":"2207.03106","title":"A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits","created":"2022-07-07","cited_by_count":28},{"id":"2203.12922","title":"Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies","created":"2022-03-24","cited_by_count":27},{"id":"2005.06670","title":"Federated Recommendation System via Differential Privacy","created":"2020-05-14","cited_by_count":26},{"id":"2109.03699","title":"Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis","created":"2021-09-08","cited_by_count":26},{"id":"2012.15511","title":"Towards Understanding Asynchronous Advantage Actor-critic: Convergence and Linear Speedup","created":"2020-12-31","cited_by_count":25},{"id":"2001.01898","title":"Reanalysis of Variance Reduced Temporal Difference Learning","created":"2020-01-07","cited_by_count":23},{"id":"2103.04972","title":"Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation","created":"2021-03-08","cited_by_count":23},{"id":"2211.13208","title":"On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation","created":"2022-11-23","cited_by_count":22},{"id":"2310.19807","title":"Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates","created":"2023-10-09","cited_by_count":21},{"id":"2404.08003","title":"Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis","created":"2024-04-09","cited_by_count":21},{"id":"2312.15023","title":"Federated Q-Learning: Linear Regret Speedup with Low Communication Cost","created":"2023-12-22","cited_by_count":19},{"id":"2203.09251","title":"Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs","created":"2022-03-17","cited_by_count":17},{"id":"2207.05852","title":"Optimistic PAC Reinforcement Learning: the Instance-Dependent View","created":"2022-07-12","cited_by_count":17},{"id":"2404.10728","title":"Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning","created":"2024-04-16","cited_by_count":17},{"id":"1906.04585","title":"Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning","created":"2019-06-09","cited_by_count":16},{"id":"1907.12530","title":"Finite-Time Performance of Distributed Temporal Difference Learning with Linear Function Approximation","created":"2019-07-25","cited_by_count":15},{"id":"2103.06473","title":"Multi-Task Federated Reinforcement Learning with Adversaries","created":"2021-03-11","cited_by_count":13},{"id":"2206.00165","title":"Byzantine-Robust Online and Offline Distributed Reinforcement Learning","created":"2022-06-01","cited_by_count":13},{"id":"2206.00177","title":"On Gap-dependent Bounds for Offline Reinforcement Learning","created":"2022-06-01","cited_by_count":13},{"id":"2210.08238","title":"Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning","created":"2022-10-15","cited_by_count":13},{"id":"2305.16246","title":"Distributed TD(0) with Almost No Communication","created":"2023-05-25","cited_by_count":13},{"id":"2402.05876","title":"Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices","created":"2024-02-08","cited_by_count":11},{"id":"2008.07841","title":"On the Convergence of Consensus Algorithms with Markovian Noise and Gradient Bias","created":"2020-08-18","cited_by_count":10},{"id":"2102.10740","title":"Communication Efficient Parallel Reinforcement Learning","created":"2021-02-22","cited_by_count":10},{"id":"2405.18795","title":"Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost","created":"2024-05-29","cited_by_count":10},{"id":"2305.06446","title":"Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation","created":"2023-05-10","cited_by_count":9},{"id":"2408.16981","title":"The Sample-Communication Complexity Trade-off in Federated Q-Learning","created":"2024-08-30","cited_by_count":9},{"id":"2410.07574","title":"Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition","created":"2024-10-10","cited_by_count":8},{"id":"2410.15612","title":"In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before An Ongoing Trajectory Terminates","created":"2024-10-21","cited_by_count":7},{"id":"1802.09184","title":"Variance Reduction Methods for Sublinear Reinforcement Learning","created":"2018-02-26","cited_by_count":6},{"id":"2301.11135","title":"FedHQL: Federated Heterogeneous Q-Learning","created":"2023-01-26","cited_by_count":6},{"id":"2403.09940","title":"Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries","created":"2024-03-15","cited_by_count":6},{"id":"2404.10635","title":"Compressed Federated Reinforcement Learning with a Generative Model","created":"2024-03-26","cited_by_count":6},{"id":"2410.22908","title":"Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents","created":"2024-10-30","cited_by_count":6}],"next_cursor":null}