{"total":18,"rows":[{"id":"2207.07150","title":"Making Linear MDPs Practical via Contrastive Representation Learning","created":"2022-07-14","cited_by_count":52,"area":null},{"id":"2202.00063","title":"Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach","created":"2022-01-31","cited_by_count":51,"area":null},{"id":"2208.09515","title":"Spectral Decomposition Representation for Reinforcement Learning","created":"2022-08-19","cited_by_count":36,"area":null},{"id":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24,"area":null},{"id":"2105.14016","title":"Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model","created":"2021-05-28","cited_by_count":18,"area":null},{"id":"2212.08765","title":"Latent Variable Representation for Reinforcement Learning","created":"2022-12-17","cited_by_count":15,"area":null},{"id":"2304.08944","title":"Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning","created":"2023-04-18","cited_by_count":15,"area":null},{"id":"2106.08414","title":"On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control","created":"2021-06-15","cited_by_count":12,"area":null},{"id":"2202.02881","title":"Approximate Policy Iteration with Bisimulation Metrics","created":"2022-02-06","cited_by_count":12,"area":null},{"id":"2311.12244","title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2206.03569","title":"Overcoming the Long Horizon Barrier for Sample-Efficient Reinforcement Learning with Latent Low-Rank Structure","created":"2022-06-07","cited_by_count":7,"area":null},{"id":"2306.13053","title":"Context-lumpable stochastic bandits","created":"2023-06-22","cited_by_count":4,"area":null},{"id":"2212.04631","title":"The Normalized Cross Density Functional: A Framework to Quantify Statistical Dependence for Random Processes","created":"2022-12-09","cited_by_count":3,"area":null},{"id":"2107.11053","title":"An Adaptive State Aggregation Algorithm for Markov Decision Processes","created":"2021-07-23","cited_by_count":2,"area":null},{"id":"2110.04232","title":"Learning Topic Models: Identifiability and Finite-Sample Analysis","created":"2021-10-08","cited_by_count":2,"area":null},{"id":"2210.01679","title":"Detection and Evaluation of Clusters within Sequential Data","created":"2022-10-04","cited_by_count":1,"area":null},{"id":"2407.18287","title":"Estimating the number of clusters of a Block Markov Chain","created":"2024-07-25","cited_by_count":1,"area":null},{"id":"2608.15920","title":"$S^3$: A Smooth Simulation Surrogate for Optimizing Discrete Abstractions of Dynamical Systems","created":"2026-08-16","cited_by_count":0,"area":null}],"next_cursor":null}