{"total":86,"rows":[{"id":"2103.10897","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","created":"2021-03-19","cited_by_count":178,"area":null},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2104.05859","title":"Rapid Exploration for Open-World Navigation with Latent Goal Models","created":"2021-04-12","cited_by_count":121,"area":null},{"id":"2204.08967","title":"When Is Partially Observable Reinforcement Learning Not Scary?","created":"2022-04-19","cited_by_count":100,"area":null},{"id":"2102.07035","title":"Model-free Representation Learning and Exploration in Low-rank MDPs","created":"2021-02-14","cited_by_count":82,"area":null},{"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":"2101.12745","title":"Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP","created":"2021-01-29","cited_by_count":45,"area":null},{"id":"2207.08229","title":"Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models","created":"2022-07-17","cited_by_count":45,"area":null},{"id":"2106.04379","title":"Learning Markov State Abstractions for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":44,"area":null},{"id":"2111.03289","title":"Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs","created":"2021-11-05","cited_by_count":44,"area":null},{"id":"2103.12690","title":"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap","created":"2021-03-23","cited_by_count":40,"area":null},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2202.03983","title":"Provable Reinforcement Learning with a Short-Term Memory","created":"2022-02-08","cited_by_count":40,"area":null},{"id":"2205.14571","title":"Provable Benefits of Representational Transfer in Reinforcement Learning","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2110.02719","title":"The Information Geometry of Unsupervised Reinforcement Learning","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2102.10960","title":"Return-Based Contrastive Representation Learning for Reinforcement Learning","created":"2021-02-22","cited_by_count":36,"area":null},{"id":"2208.09515","title":"Spectral Decomposition Representation for Reinforcement Learning","created":"2022-08-19","cited_by_count":36,"area":null},{"id":"2206.12020","title":"Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems","created":"2022-06-24","cited_by_count":35,"area":null},{"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,"area":null},{"id":"2206.07659","title":"Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2302.03201","title":"Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR","created":"2023-02-07","cited_by_count":32,"area":null},{"id":"2206.03446","title":"Learning in Observable POMDPs, without Computationally Intractable Oracles","created":"2022-06-07","cited_by_count":30,"area":null},{"id":"2106.07278","title":"Which Mutual-Information Representation Learning Objectives are Sufficient for Control?","created":"2021-06-14","cited_by_count":29,"area":null},{"id":"2206.05900","title":"Provable Benefit of Multitask Representation Learning in Reinforcement Learning","created":"2022-06-13","cited_by_count":29,"area":null},{"id":"2110.08847","title":"Provable RL with Exogenous Distractors via Multistep Inverse Dynamics","created":"2021-10-17","cited_by_count":28,"area":null},{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2206.10770","title":"On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL","created":"2022-06-21","cited_by_count":27,"area":null},{"id":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2206.04282","title":"Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2207.14800","title":"Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning","created":"2022-07-29","cited_by_count":26,"area":null},{"id":"2107.07184","title":"MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning","created":"2021-07-15","cited_by_count":24,"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":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2304.05889","title":"Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL","created":"2023-04-12","cited_by_count":22,"area":null},{"id":"2106.02193","title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2102.09850","title":"Model-Invariant State Abstractions for Model-Based Reinforcement Learning","created":"2021-02-19","cited_by_count":18,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2307.03997","title":"Efficient Model-Free Exploration in Low-Rank MDPs","created":"2023-07-08","cited_by_count":16,"area":null},{"id":"2212.08765","title":"Latent Variable Representation for Reinforcement Learning","created":"2022-12-17","cited_by_count":15,"area":null},{"id":"2303.10859","title":"Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs","created":"2023-03-20","cited_by_count":14,"area":null},{"id":"2103.11559","title":"Provably Correct Optimization and Exploration with Non-linear Policies","created":"2021-03-22","cited_by_count":13,"area":null},{"id":"2106.11519","title":"Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2212.13835","title":"Representation Learning in Deep RL via Discrete Information Bottleneck","created":"2022-12-28","cited_by_count":13,"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":"2202.06545","title":"Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization","created":"2022-02-14","cited_by_count":12,"area":null},{"id":"2211.00247","title":"Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning","created":"2022-11-01","cited_by_count":11,"area":null},{"id":"2307.04354","title":"Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data","created":"2023-07-10","cited_by_count":11,"area":null},{"id":"2403.11940","title":"Multistep Inverse Is Not All You Need","created":"2024-03-18","cited_by_count":11,"area":null},{"id":"2203.08248","title":"Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling","created":"2022-03-15","cited_by_count":10,"area":null},{"id":"2211.10282","title":"Exploring through Random Curiosity with General Value Functions","created":"2022-11-18","cited_by_count":10,"area":null},{"id":"2310.06793","title":"Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning","created":"2023-10-10","cited_by_count":10,"area":null},{"id":"2402.06187","title":"Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss","created":"2024-02-09","cited_by_count":10,"area":null},{"id":"2305.16483","title":"Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2306.12356","title":"Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2105.01136","title":"Learning Good State and Action Representations via Tensor Decomposition","created":"2021-05-03","cited_by_count":7,"area":null},{"id":"2203.11369","title":"Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL","created":"2022-03-21","cited_by_count":7,"area":null},{"id":"2206.08364","title":"Interaction-Grounded Learning with Action-inclusive Feedback","created":"2022-06-16","cited_by_count":7,"area":null},{"id":"2210.14492","title":"Provable Safe Reinforcement Learning with Binary Feedback","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2304.00046","title":"Accelerating exploration and representation learning with offline pre-training","created":"2023-03-31","cited_by_count":7,"area":null},{"id":"2106.07814","title":"Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2107.07394","title":"Explore and Control with Adversarial Surprise","created":"2021-07-12","cited_by_count":6,"area":null},{"id":"2210.03325","title":"Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworks","created":"2022-10-07","cited_by_count":5,"area":null},{"id":"2210.07536","title":"A Reinforcement Learning Approach to Estimating Long-term Treatment Effects","created":"2022-10-14","cited_by_count":5,"area":null},{"id":"2403.09701","title":"A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2210.16872","title":"Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction","created":"2022-10-30","cited_by_count":4,"area":null},{"id":"2306.13053","title":"Context-lumpable stochastic bandits","created":"2023-06-22","cited_by_count":4,"area":null},{"id":"2307.02884","title":"Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight","created":"2023-07-06","cited_by_count":4,"area":null},{"id":"2311.03534","title":"PcLast: Discovering Plannable Continuous Latent States","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2311.03564","title":"Low-Rank MDPs with Continuous Action Spaces","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2210.13075","title":"Hardness in Markov Decision Processes: Theory and Practice","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2211.07614","title":"Towards Data-Driven Offline Simulations for Online Reinforcement Learning","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2410.03016","title":"Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory","created":"2024-10-03","cited_by_count":3,"area":null},{"id":"2205.14237","title":"Provably Sample-Efficient RL with Side Information about Latent Dynamics","created":"2022-05-27","cited_by_count":2,"area":null},{"id":"2206.01192","title":"Uniqueness and Complexity of Inverse MDP Models","created":"2022-06-02","cited_by_count":2,"area":null},{"id":"2305.00654","title":"Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2503.21018","title":"Offline Action-Free Learning of Ex-BMDPs by Comparing Diverse Datasets","created":"2025-03-26","cited_by_count":2,"area":null},{"id":"2106.15503","title":"Curious Explorer: a provable exploration strategy in Policy Learning","created":"2021-06-29","cited_by_count":1,"area":null},{"id":"2404.09123","title":"Provable Interactive Learning with Hindsight Instruction Feedback","created":"2024-04-14","cited_by_count":1,"area":null},{"id":"2205.02678","title":"Chemoreception and chemotaxis of a three-sphere swimmer","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2209.06356","title":"Using Forwards-Backwards Models to Approximate MDP Homomorphisms","created":"2022-09-14","cited_by_count":0,"area":null},{"id":"2303.07397","title":"Fast exploration and learning of latent graphs with aliased observations","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2309.08622","title":"Representation Learning in Low-rank Slate-based Recommender Systems","created":"2023-09-10","cited_by_count":0,"area":null}],"next_cursor":null}