{"total":109,"rows":[{"id":"2404.03578","title":"Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms","created":"2024-04-04","cited_by_count":26,"area":"deeprl"},{"id":"2402.15776","title":"Truly No-Regret Learning in Constrained MDPs","created":"2024-02-24","cited_by_count":23,"area":"deeprl"},{"id":"2401.13884","title":"Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation","created":"2024-01-25","cited_by_count":17,"area":"deeprl"},{"id":"2409.20521","title":"Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning","created":"2024-09-30","cited_by_count":16,"area":"deeprl"},{"id":"2408.08994","title":"Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds","created":"2024-08-16","cited_by_count":11,"area":"deeprl"},{"id":"2402.05724","title":"Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL","created":"2024-02-08","cited_by_count":9,"area":"deeprl"},{"id":"2404.12598","title":"Continuous-time Risk-sensitive Reinforcement Learning via Quadratic Variation Penalty","created":"2024-04-19","cited_by_count":9,"area":"deeprl"},{"id":"2407.13743","title":"Optimistic Q-learning for average reward and episodic reinforcement learning","created":"2024-07-18","cited_by_count":9,"area":"deeprl"},{"id":"2408.16981","title":"The Sample-Communication Complexity Trade-off in Federated Q-Learning","created":"2024-08-30","cited_by_count":9,"area":"deeprl"},{"id":"2403.00222","title":"Efficient Reinforcement Learning for Global Decision Making in the Presence of Local Agents at Scale","created":"2024-03-01","cited_by_count":8,"area":"deeprl"},{"id":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","cited_by_count":8,"area":"deeprl"},{"id":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"id":"2412.14355","title":"Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference","created":"2024-12-18","cited_by_count":7,"area":"deeprl"},{"id":"2403.04568","title":"Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition","created":"2024-03-07","cited_by_count":6,"area":"deeprl"},{"id":"2403.10738","title":"Horizon-Free Regret for Linear Markov Decision Processes","created":"2024-03-15","cited_by_count":6,"area":"deeprl"},{"id":"2403.11637","title":"The Value of Reward Lookahead in Reinforcement Learning","created":"2024-03-18","cited_by_count":6,"area":"deeprl"},{"id":"2406.13909","title":"Beyond Optimism: Exploration With Partially Observable Rewards","created":"2024-06-20","cited_by_count":6,"area":"deeprl"},{"id":"2505.11478","title":"Automatic Reward Shaping from Confounded Offline Data","created":"2025-05-16","cited_by_count":6,"area":"deeprl"},{"id":"2508.03768","title":"ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning","created":"2025-08-05","cited_by_count":6,"area":"deeprl"},{"id":"2405.00282","title":"MF-OML: Online Mean-Field Reinforcement Learning with Occupation Measures for Large Population Games","created":"2024-05-01","cited_by_count":5,"area":"deeprl"},{"id":"2406.11810","title":"Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics","created":"2024-06-17","cited_by_count":5,"area":"deeprl"},{"id":"2407.00801","title":"Model-Free Active Exploration in Reinforcement Learning","created":"2024-06-30","cited_by_count":5,"area":"deeprl"},{"id":"2407.03065","title":"Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes","created":"2024-07-03","cited_by_count":5,"area":"deeprl"},{"id":"2510.14129","title":"Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL","created":"2025-10-15","cited_by_count":5,"area":"deeprl"},{"id":"2606.00151","title":"Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying","created":"2026-05-29","cited_by_count":5,"area":"deeprl"},{"id":"2401.08961","title":"Cascading Reinforcement Learning","created":"2024-01-17","cited_by_count":4,"area":"deeprl"},{"id":"2402.13930","title":"Enhancing Reinforcement Learning Agents with Local Guides","created":"2024-02-21","cited_by_count":4,"area":"deeprl"},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2502.01876","title":"Reinforcement Learning with Segment Feedback","created":"2025-02-03","cited_by_count":4,"area":"deeprl"},{"id":"2502.02869","title":"Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds","created":"2025-02-05","cited_by_count":4,"area":"deeprl"},{"id":"2506.07040","title":"Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning","created":"2025-06-08","cited_by_count":4,"area":"deeprl"},{"id":"2510.16132","title":"A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies","created":"2025-10-17","cited_by_count":4,"area":"deeprl"},{"id":"2510.19372","title":"On the Hardness of Reinforcement Learning with Transition Look-Ahead","created":"2025-10-22","cited_by_count":4,"area":"deeprl"},{"id":"2510.20725","title":"No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes","created":"2025-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2401.05233","title":"Taming \"data-hungry\" reinforcement learning? Stability in continuous state-action spaces","created":"2024-01-10","cited_by_count":3,"area":"deeprl"},{"id":"2402.18159","title":"Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation","created":"2024-02-28","cited_by_count":3,"area":"deeprl"},{"id":"2409.14557","title":"Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning","created":"2024-09-22","cited_by_count":3,"area":"deeprl"},{"id":"2410.08868","title":"On the Convergence of Single-Timescale Actor-Critic","created":"2024-10-11","cited_by_count":3,"area":"deeprl"},{"id":"2512.06244","title":"Auto-exploration for online reinforcement learning","created":"2025-12-06","cited_by_count":3,"area":"deeprl"},{"id":"2512.15036","title":"Spectral Representation-based Reinforcement Learning","created":"2025-12-17","cited_by_count":3,"area":"deeprl"},{"id":"2601.13642","title":"Sample Complexity of Average-Reward Q-Learning: From Single-agent to Federated Reinforcement Learning","created":"2026-01-20","cited_by_count":3,"area":"deeprl"},{"id":"2405.17832","title":"Mollification Effects of Policy Gradient Methods","created":"2024-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2406.15250","title":"Open Problem: Order Optimal Regret Bounds for Kernel-Based Reinforcement Learning","created":"2024-06-21","cited_by_count":2,"area":"deeprl"},{"id":"2408.16882","title":"Coverage Analysis of Multi-Environment Q-Learning Algorithms for Wireless Network Optimization","created":"2024-08-29","cited_by_count":2,"area":"deeprl"},{"id":"2409.05908","title":"Faster Q-Learning Algorithms for Restless Bandits","created":"2024-09-06","cited_by_count":2,"area":"deeprl"},{"id":"2409.14178","title":"FlowRL: Flow-Augmented Few-Shot Reinforcement Learning for Semi-Structured Sensor Data","created":"2024-09-21","cited_by_count":2,"area":"deeprl"},{"id":"2503.00810","title":"Minimax Optimal Reinforcement Learning with Quasi-Optimism","created":"2025-03-02","cited_by_count":2,"area":"deeprl"},{"id":"2506.04626","title":"Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning","created":"2025-06-05","cited_by_count":2,"area":"deeprl"},{"id":"2506.24005","title":"Provably Efficient and Agile Randomized Q-Learning","created":"2025-06-30","cited_by_count":2,"area":"deeprl"},{"id":"2507.11706","title":"Reinforcement Learning from Adversarial Preferences in Tabular MDPs","created":"2025-07-15","cited_by_count":2,"area":"deeprl"},{"id":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","cited_by_count":2,"area":"deeprl"},{"id":"2603.02862","title":"Learning in Markov Decision Processes with Exogenous Dynamics","created":"2026-03-03","cited_by_count":2,"area":"deeprl"},{"id":"2603.27884","title":"Near-Optimal Primal-Dual Algorithm for Learning Linear Mixture CMDPs with Adversarial Rewards","created":"2026-03-29","cited_by_count":2,"area":"deeprl"},{"id":"2404.07559","title":"Differentially Private Reinforcement Learning with Self-Play","created":"2024-04-11","cited_by_count":1,"area":"deeprl"},{"id":"2409.15963","title":"Provably Efficient Exploration in Inverse Constrained Reinforcement Learning","created":"2024-09-24","cited_by_count":1,"area":"deeprl"},{"id":"2410.13463","title":"Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach","created":"2024-10-17","cited_by_count":1,"area":"deeprl"},{"id":"2502.07715","title":"Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning","created":"2025-02-11","cited_by_count":1,"area":"deeprl"},{"id":"2503.18980","title":"CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning","created":"2025-03-23","cited_by_count":1,"area":"deeprl"},{"id":"2503.22775","title":"Invariant Control Strategies for Active Flow Control using Graph Neural Networks","created":"2025-03-28","cited_by_count":1,"area":"deeprl"},{"id":"2505.11044","title":"Exploration by Random Distribution Distillation","created":"2025-05-16","cited_by_count":1,"area":"deeprl"},{"id":"2506.00917","title":"Q-learning with Posterior Sampling","created":"2025-06-01","cited_by_count":1,"area":"deeprl"},{"id":"2507.12383","title":"Improving Reinforcement Learning Sample-Efficiency using Local Approximation","created":"2025-07-16","cited_by_count":1,"area":"deeprl"},{"id":"2507.22854","title":"A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model","created":"2025-07-30","cited_by_count":1,"area":"deeprl"},{"id":"2510.03181","title":"Q-Learning with Shift-Aware Upper Confidence Bound in Non-Stationary Reinforcement Learning","created":"2025-10-03","cited_by_count":1,"area":"deeprl"},{"id":"2510.06647","title":"Q-Learning with Fine-Grained Gap-Dependent Regret","created":"2025-10-08","cited_by_count":1,"area":"deeprl"},{"id":"2511.18247","title":"Tail Distribution of Regret in Optimistic Reinforcement Learning","created":"2025-11-23","cited_by_count":1,"area":"deeprl"},{"id":"2602.02260","title":"Learning Markov Decision Processes under Fully Bandit Feedback","created":"2026-02-02","cited_by_count":1,"area":"deeprl"},{"id":"2602.15076","title":"Near-Optimal Sample Complexity for Online Constrained MDPs","created":"2026-02-16","cited_by_count":1,"area":"deeprl"},{"id":"2605.00654","title":"Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation","created":"2026-05-01","cited_by_count":1,"area":"deeprl"},{"id":"2609.00193","title":"Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost","created":"2026-08-31","cited_by_count":1,"area":"deeprl"},{"id":"2404.00686","title":"Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning","created":"2024-03-31","cited_by_count":0,"area":"deeprl"},{"id":"2407.21260","title":"Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation","created":"2024-07-31","cited_by_count":0,"area":"deeprl"},{"id":"2408.06544","title":"Variance-Reduced Cascade Q-learning: Algorithms and Sample Complexity","created":"2024-08-13","cited_by_count":0,"area":"deeprl"},{"id":"2409.18439","title":"State-free Reinforcement Learning","created":"2024-09-27","cited_by_count":0,"area":"deeprl"},{"id":"2501.13394","title":"Concurrent Learning with Aggregated States via Randomized Least Squares Value Iteration","created":"2025-01-23","cited_by_count":0,"area":"deeprl"},{"id":"2504.05978","title":"Smart Exploration in Reinforcement Learning using Bounded Uncertainty Models","created":"2025-04-08","cited_by_count":0,"area":"deeprl"},{"id":"2509.02737","title":"Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient","created":"2025-09-02","cited_by_count":0,"area":"deeprl"},{"id":"2510.11933","title":"Efficient Restarts in Non-Stationary Model-Free Reinforcement Learning","created":"2025-10-13","cited_by_count":0,"area":"deeprl"},{"id":"2510.19528","title":"Learning Upper Lower Value Envelopes to Shape Online RL: A Principled Approach","created":"2025-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2511.03473","title":"Reinforcement Learning Using known Invariances","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2511.03595","title":"Tensor-Efficient High-Dimensional Q-learning","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2511.17351","title":"Convergence and stability of Q-learning in Hierarchical Reinforcement Learning","created":"2025-11-21","cited_by_count":0,"area":"deeprl"},{"id":"2601.10418","title":"Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching","created":"2026-01-15","cited_by_count":0,"area":"deeprl"},{"id":"2602.00781","title":"Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding","created":"2026-01-31","cited_by_count":0,"area":"deeprl"},{"id":"2602.01505","title":"Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum","created":"2026-02-02","cited_by_count":0,"area":"deeprl"},{"id":"2603.03480","title":"Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning","created":"2026-03-03","cited_by_count":0,"area":"deeprl"},{"id":"2603.23461","title":"End-to-End Efficient RL for Linear Bellman Complete MDPs with Deterministic Transitions","created":"2026-03-24","cited_by_count":0,"area":"deeprl"},{"id":"2603.27066","title":"Dynamic resource matching in manufacturing using deep reinforcement learning","created":"2026-03-28","cited_by_count":0,"area":"deeprl"},{"id":"2605.01242","title":"Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs","created":"2026-05-02","cited_by_count":0,"area":"deeprl"},{"id":"2605.03125","title":"Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation","created":"2026-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2605.06373","title":"Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under $\\tau$-Mixing","created":"2026-05-07","cited_by_count":0,"area":"deeprl"},{"id":"2605.07218","title":"Improved Model-based Reinforcement Learning with Smooth Kernels","created":"2026-05-08","cited_by_count":0,"area":"deeprl"},{"id":"2605.15692","title":"Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2605.20592","title":"ReversedQ: Opportunities for Faster Q-Learning in Episodic Online Reinforcement Learning","created":"2026-05-20","cited_by_count":0,"area":"deeprl"},{"id":"2605.24345","title":"Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs","created":"2026-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2606.01952","title":"Randomized Least Squares Value Iteration itself is Joint Differentially Private","created":"2026-06-01","cited_by_count":0,"area":"deeprl"},{"id":"2606.16846","title":"Deep Q-Learning on H\\\"older Spaces","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2606.20107","title":"Quantile of Means: A Bonus-Free Ensemble Method for Minimax Optimal Reinforcement Learning","created":"2026-06-18","cited_by_count":0,"area":"deeprl"},{"id":"2607.06935","title":"Mathematical methods of reinforcement learning","created":"2026-07-08","cited_by_count":0,"area":"deeprl"},{"id":"2607.21302","title":"Expert Behavior Prior Reinforcement Learning","created":"2026-07-23","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}