{"total":117,"rows":[{"id":"2110.01548","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","created":"2021-10-04","cited_by_count":302,"area":"offlinerl"},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288,"area":null},{"id":"2107.00591","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","created":"2021-07-01","cited_by_count":214,"area":"offlinerl"},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2210.13846","title":"Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning","created":"2022-10-25","cited_by_count":34,"area":"offlinerl"},{"id":"2102.08159","title":"RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents","created":"2021-02-16","cited_by_count":31,"area":null},{"id":"2103.00445","title":"Ensemble Bootstrapping for Q-Learning","created":"2021-02-28","cited_by_count":31,"area":null},{"id":"2102.09225","title":"Continuous Doubly Constrained Batch Reinforcement Learning","created":"2021-02-18","cited_by_count":27,"area":"offlinerl"},{"id":"2103.06469","title":"Generalizable Episodic Memory for Deep Reinforcement Learning","created":"2021-03-11","cited_by_count":23,"area":null},{"id":"2106.03050","title":"Efficient Continuous Control with Double Actors and Regularized Critics","created":"2021-06-06","cited_by_count":21,"area":null},{"id":"2406.18420","title":"Mixture of Experts in a Mixture of RL settings","created":"2024-06-26","cited_by_count":21,"area":"moe"},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2306.06871","title":"ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles","created":"2023-06-12","cited_by_count":20,"area":"offlinerl"},{"id":"2103.11883","title":"Regularized Softmax Deep Multi-Agent $Q$-Learning","created":"2021-03-22","cited_by_count":19,"area":null},{"id":"2110.03375","title":"Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning","created":"2021-10-07","cited_by_count":18,"area":null},{"id":"2403.05996","title":"Dissecting Deep RL with High Update Ratios: Combatting Value Divergence","created":"2024-03-09","cited_by_count":17,"area":"deeprl"},{"id":"2409.04792","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","created":"2024-09-07","cited_by_count":17,"area":"deeprl"},{"id":"2202.05404","title":"Regularized Q-learning","created":"2022-02-11","cited_by_count":16,"area":null},{"id":"2303.02618","title":"Ensemble Reinforcement Learning: A Survey","created":"2023-03-05","cited_by_count":16,"area":null},{"id":"2410.08896","title":"MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL","created":"2024-10-11","cited_by_count":16,"area":"deeprl"},{"id":"2006.07442","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","created":"2020-06-12","cited_by_count":13,"area":"offlinerl"},{"id":"2209.07670","title":"Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks","created":"2022-09-16","cited_by_count":13,"area":null},{"id":"2309.16973","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","created":"2023-09-29","cited_by_count":12,"area":"offlinerl"},{"id":"2310.01365","title":"Elephant Neural Networks: Born to Be a Continual Learner","created":"2023-10-02","cited_by_count":10,"area":null},{"id":"2203.11526","title":"Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Tasks","created":"2022-03-22","cited_by_count":9,"area":null},{"id":"2205.10868","title":"Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2306.11918","title":"Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2507.02712","title":"A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control","created":"2025-07-03","cited_by_count":9,"area":"deeprl"},{"id":"2201.13357","title":"DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning","created":"2022-01-31","cited_by_count":8,"area":null},{"id":"2207.11762","title":"Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System","created":"2022-07-24","cited_by_count":8,"area":null},{"id":"2401.03137","title":"SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning","created":"2024-01-06","cited_by_count":8,"area":null},{"id":"2111.09159","title":"Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance","created":"2021-11-17","cited_by_count":7,"area":null},{"id":"2404.12754","title":"Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation","created":"2024-04-19","cited_by_count":7,"area":"deeprl"},{"id":"2501.08669","title":"SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning","created":"2025-01-15","cited_by_count":7,"area":"deeprl"},{"id":"2111.12673","title":"Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning","created":"2021-11-24","cited_by_count":6,"area":null},{"id":"2401.08850","title":"REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes","created":"2024-01-16","cited_by_count":6,"area":"deeprl"},{"id":"2405.04342","title":"The Curse of Diversity in Ensemble-Based Exploration","created":"2024-05-07","cited_by_count":6,"area":"deeprl"},{"id":"2410.08540","title":"Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2410.09580","title":"SAPIENT: Mastering Multi-turn Conversational Recommendation with Strategic Planning and Monte Carlo Tree Search","created":"2024-10-12","cited_by_count":6,"area":null},{"id":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"id":"2109.10552","title":"MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2110.04698","title":"A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets","created":"2021-10-10","cited_by_count":5,"area":"offlinerl"},{"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":"2310.11138","title":"Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control","created":"2023-10-17","cited_by_count":5,"area":null},{"id":"2402.05476","title":"Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimization","created":"2024-02-08","cited_by_count":5,"area":"deeprl"},{"id":"2405.02576","title":"CTD4 -- A Deep Continuous Distributional Actor-Critic Agent with a Kalman Fusion of Multiple Critics","created":"2024-05-04","cited_by_count":5,"area":"deeprl"},{"id":"2405.10310","title":"Stochastic Q-learning for Large Discrete Action Spaces","created":"2024-05-16","cited_by_count":5,"area":"deeprl"},{"id":"2406.19768","title":"Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors","created":"2024-06-28","cited_by_count":5,"area":"deeprl"},{"id":"2510.22686","title":"FlowCritic: Bridging Value Estimation with Flow Matching in Reinforcement Learning","created":"2025-10-26","cited_by_count":5,"area":"diffusion"},{"id":"2109.14419","title":"On the Estimation Bias in Double Q-Learning","created":"2021-09-29","cited_by_count":4,"area":null},{"id":"2311.18393","title":"Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control","created":"2023-11-30","cited_by_count":4,"area":null},{"id":"2402.08022","title":"Leveraging Digital Cousins for Ensemble Q-Learning in Large-Scale Wireless Networks","created":"2024-02-12","cited_by_count":4,"area":"deeprl"},{"id":"2403.13097","title":"Simple Ingredients for Offline Reinforcement Learning","created":"2024-03-19","cited_by_count":4,"area":"offlinerl"},{"id":"2103.02225","title":"Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction","created":"2021-03-03","cited_by_count":3,"area":null},{"id":"2111.02787","title":"Balanced Q-learning: Combining the Influence of Optimistic and Pessimistic Targets","created":"2021-11-03","cited_by_count":3,"area":null},{"id":"2402.00823","title":"SLIM: Skill Learning with Multiple Critics","created":"2024-02-01","cited_by_count":3,"area":"deeprl"},{"id":"2405.16195","title":"Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning","created":"2024-05-25","cited_by_count":3,"area":"deeprl"},{"id":"2109.10736","title":"Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods","created":"2021-09-22","cited_by_count":2,"area":null},{"id":"2110.13523","title":"Automating Control of Overestimation Bias for Reinforcement Learning","created":"2021-10-26","cited_by_count":2,"area":null},{"id":"2110.14818","title":"Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates","created":"2021-10-28","cited_by_count":2,"area":null},{"id":"2206.09627","title":"Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration","created":"2022-06-20","cited_by_count":2,"area":null},{"id":"2302.09875","title":"Backstepping Temporal Difference Learning","created":"2023-02-20","cited_by_count":2,"area":null},{"id":"2306.16750","title":"Eigensubspace of Temporal-Difference Dynamics and How It Improves Value Approximation in Reinforcement Learning","created":"2023-06-29","cited_by_count":2,"area":null},{"id":"2402.11604","title":"Self-evolving Autoencoder Embedded Q-Network","created":"2024-02-18","cited_by_count":2,"area":"deeprl"},{"id":"2405.18289","title":"Highway Reinforcement Learning","created":"2024-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2409.16450","title":"A Multi-Agent Multi-Environment Mixed Q-Learning for Partially Decentralized Wireless Network Optimization","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2510.02590","title":"Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning","created":"2025-10-02","cited_by_count":2,"area":"deeprl"},{"id":"2510.14503","title":"Learning to Undo: Rollback-Augmented Reinforcement Learning with Reversibility Signals","created":"2025-10-16","cited_by_count":2,"area":"deeprl"},{"id":"2102.03866","title":"Model-Augmented Q-learning","created":"2021-02-07","cited_by_count":1,"area":null},{"id":"2110.09712","title":"Balancing Value Underestimation and Overestimation with Realistic Actor-Critic","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2111.06780","title":"AWD3: Dynamic Reduction of the Estimation Bias","created":"2021-11-12","cited_by_count":1,"area":null},{"id":"2203.10445","title":"Smoothing Advantage Learning","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2301.02375","title":"Centralized Cooperative Exploration Policy for Continuous Control Tasks","created":"2023-01-06","cited_by_count":1,"area":null},{"id":"2304.09087","title":"MDDL: A Framework for Reinforcement Learning-based Position Allocation in Multi-Channel Feed","created":"2023-04-17","cited_by_count":1,"area":null},{"id":"2305.14859","title":"Utility-Probability Duality of Neural Networks","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2308.07351","title":"IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2309.14471","title":"Adapting Double Q-Learning for Continuous Reinforcement Learning","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2310.06286","title":"Suppressing Overestimation in Q-Learning through Adversarial Behaviors","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2402.09078","title":"Exploiting Estimation Bias in Clipped Double Q-Learning for Continous Control Reinforcement Learning Tasks","created":"2024-02-14","cited_by_count":1,"area":"deeprl"},{"id":"2405.07223","title":"Ensemble Successor Representations for Task Generalization in Offline-to-Online Reinforcement Learning","created":"2024-05-12","cited_by_count":1,"area":"offlinerl"},{"id":"2405.08638","title":"vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement","created":"2024-05-14","cited_by_count":1,"area":"deeprl"},{"id":"2411.08360","title":"Coverage Analysis for Digital Cousin Selection -- Improving Multi-Environment Q-Learning","created":"2024-11-13","cited_by_count":1,"area":"deeprl"},{"id":"2506.05968","title":"Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning","created":"2025-06-06","cited_by_count":1,"area":"deeprl"},{"id":"2506.19478","title":"ADDQ: Adaptive Distributional Double Q-Learning","created":"2025-06-24","cited_by_count":1,"area":"deeprl"},{"id":"2507.00275","title":"Deep Double Q-learning","created":"2025-06-30","cited_by_count":1,"area":"deeprl"},{"id":"2508.01329","title":"Is Exploration or Optimization the Problem for Deep Reinforcement Learning?","created":"2025-08-02","cited_by_count":1,"area":"deeprl"},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.07746","title":"A Tutorial: An Intuitive Explanation of Offline Reinforcement Learning Theory","created":"2025-08-11","cited_by_count":1,"area":"offlinerl"},{"id":"2601.11953","title":"Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration","created":"2026-01-17","cited_by_count":1,"area":"deeprl"},{"id":"2102.11717","title":"Greedy-Step Off-Policy Reinforcement Learning","created":"2021-02-23","cited_by_count":0,"area":null},{"id":"2104.08359","title":"In Defense of the Paper","created":"2021-04-16","cited_by_count":0,"area":null},{"id":"2109.11788","title":"Parameter-free Reduction of the Estimation Bias in Deep Reinforcement Learning for Deterministic Policy Gradients","created":"2021-09-24","cited_by_count":0,"area":null},{"id":"2202.02693","title":"Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning","created":"2022-02-06","cited_by_count":0,"area":null},{"id":"2205.07467","title":"$q$-Munchausen Reinforcement Learning","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2210.05262","title":"Factors of Influence of the Overestimation Bias of Q-Learning","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2210.11111","title":"The Pump Scheduling Problem: A Real-World Scenario for Reinforcement Learning","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2311.03711","title":"Mitigating Estimation Errors by Twin TD-Regularized Actor and Critic for Deep Reinforcement Learning","created":"2023-11-07","cited_by_count":0,"area":null},{"id":"2401.05341","title":"Stable Online and Offline Reinforcement Learning for Antibody CDRH3 Design","created":"2023-11-29","cited_by_count":0,"area":null},{"id":"2402.05950","title":"SQT -- std $Q$-target","created":"2024-02-03","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}