{"total":106,"rows":[{"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":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126,"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":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2106.04217","title":"Dynamic Sparse Training for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":49,"area":null},{"id":"1907.04543","title":"An Optimistic Perspective on Offline Reinforcement Learning","created":"2019-07-10","cited_by_count":37,"area":"offlinerl"},{"id":"2402.00856","title":"Towards Efficient Exact Optimization of Language Model Alignment","created":"2024-02-01","cited_by_count":37,"area":"alignment"},{"id":"2108.06084","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","created":"2021-08-13","cited_by_count":36,"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":"2103.00445","title":"Ensemble Bootstrapping for Q-Learning","created":"2021-02-28","cited_by_count":31,"area":null},{"id":"2110.11222","title":"Is High Variance Unavoidable in RL? A Case Study in Continuous Control","created":"2021-10-21","cited_by_count":28,"area":null},{"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":"2406.17523","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning","created":"2024-06-25","cited_by_count":21,"area":"deeprl"},{"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":"2205.09284","title":"Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble","created":"2022-05-19","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":"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":"2310.20287","title":"Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents","created":"2023-10-31","cited_by_count":12,"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":"2306.11918","title":"Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2110.08896","title":"Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization","created":"2021-10-17","cited_by_count":8,"area":null},{"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":"2306.07541","title":"A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning","created":"2023-06-13","cited_by_count":8,"area":"offlinerl"},{"id":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","cited_by_count":8,"area":"deeprl"},{"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":"2301.00141","title":"Self-Activating Neural Ensembles for Continual Reinforcement Learning","created":"2022-12-31","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":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2307.10936","title":"PASTA: Pretrained Action-State Transformer Agents","created":"2023-07-20","cited_by_count":6,"area":"agents"},{"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":"2604.19485","title":"EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training","created":"2026-04-21","cited_by_count":6,"area":"lr"},{"id":"2102.03127","title":"Experience-Based Heuristic Search: Robust Motion Planning with Deep Q-Learning","created":"2021-02-05","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":"2302.03439","title":"Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning","created":"2023-02-07","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":"2502.19859","title":"IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic","created":"2025-02-27","cited_by_count":5,"area":"offlinerl"},{"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":"2103.10176","title":"Maximum Entropy Reinforcement Learning with Mixture Policies","created":"2021-03-18","cited_by_count":4,"area":null},{"id":"2109.14419","title":"On the Estimation Bias in Double Q-Learning","created":"2021-09-29","cited_by_count":4,"area":null},{"id":"2209.02106","title":"Prediction Based Decision Making for Autonomous Highway Driving","created":"2022-09-05","cited_by_count":4,"area":"driving"},{"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":"2103.02225","title":"Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction","created":"2021-03-03","cited_by_count":3,"area":null},{"id":"2107.08083","title":"Robust Risk-Sensitive Reinforcement Learning Agents for Trading Markets","created":"2021-07-16","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":"2409.19231","title":"Double Actor-Critic with TD Error-Driven Regularization in Reinforcement Learning","created":"2024-09-28","cited_by_count":3,"area":"deeprl"},{"id":"2501.00913","title":"$\\beta$-DQN: Improving Deep Q-Learning By Evolving the Behavior","created":"2025-01-01","cited_by_count":3,"area":"deeprl"},{"id":"2501.06700","title":"Average Reward Reinforcement Learning for Wireless Radio Resource Management","created":"2025-01-12","cited_by_count":3,"area":"deeprl"},{"id":"2501.12739","title":"Multiscale Training of Convolutional Neural Networks","created":"2025-01-22","cited_by_count":3,"area":null},{"id":"2105.05473","title":"Interpretable performance analysis towards offline reinforcement learning: A dataset perspective","created":"2021-05-12","cited_by_count":2,"area":"offlinerl"},{"id":"2107.01904","title":"Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning","created":"2021-07-05","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":"2112.03404","title":"Learning to Detect Critical Nodes in Sparse Graphs via Feature Importance Awareness","created":"2021-12-03","cited_by_count":2,"area":null},{"id":"2201.12739","title":"Do We Need to Penalize Variance of Losses for Learning with Label Noise?","created":"2022-01-30","cited_by_count":2,"area":null},{"id":"2209.09329","title":"MAN: Multi-Action Networks Learning","created":"2022-09-19","cited_by_count":2,"area":null},{"id":"2307.16152","title":"Variance Control for Distributional Reinforcement Learning","created":"2023-07-30","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":"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":"2409.16450","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":"2412.02029","title":"Learning Ensembles of Vision-based Safety Control Filters","created":"2024-12-02","cited_by_count":2,"area":null},{"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":"2101.06906","title":"Stable deep reinforcement learning method by predicting uncertainty in rewards as a subtask","created":"2021-01-18","cited_by_count":1,"area":null},{"id":"2107.04987","title":"Coordinate-wise Control Variates for Deep Policy Gradients","created":"2021-07-11","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":"2209.10072","title":"On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2402.06266","title":"Issues with Value-Based Multi-objective Reinforcement Learning: Value Function Interference and Overestimation Sensitivity","created":"2024-02-09","cited_by_count":1,"area":"deeprl"},{"id":"2402.09550","title":"Dataset Clustering for Improved Offline Policy Learning","created":"2024-02-14","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":"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":"2508.10530","title":"Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?","created":"2025-08-14","cited_by_count":1,"area":"alignment"},{"id":"2512.23773","title":"FineFT: Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading","created":"2025-12-29","cited_by_count":1,"area":"deeprl"},{"id":"2205.03819","title":"Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods","created":"2022-05-08","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":"2209.15078","title":"Online Weighted Q-Ensembles for Reduced Hyperparameter Tuning in Reinforcement Learning","created":"2022-09-29","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":"2310.14009","title":"One is More: Diverse Perspectives within a Single Network for Efficient DRL","created":"2023-10-21","cited_by_count":0,"area":null},{"id":"2312.15458","title":"Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation","created":"2023-12-24","cited_by_count":0,"area":null},{"id":"2402.00468","title":"RadDQN: a Deep Q Learning-based Architecture for Finding Time-efficient Minimum Radiation Exposure Pathway","created":"2024-02-01","cited_by_count":0,"area":"deeprl"},{"id":"2405.02201","title":"Regularized Q-learning through Robust Averaging","created":"2024-05-03","cited_by_count":0,"area":"deeprl"},{"id":"2412.10381","title":"Supervised Learning-enhanced Multi-Group Actor Critic for Live Stream Allocation in Feed","created":"2024-11-28","cited_by_count":0,"area":"deeprl"},{"id":"2501.11818","title":"Group-Agent Reinforcement Learning with Heterogeneous Agents","created":"2025-01-21","cited_by_count":0,"area":"deeprl"},{"id":"2504.09929","title":"Moderate Actor-Critic Methods: Controlling Overestimation Bias via Expectile Loss","created":"2025-04-14","cited_by_count":0,"area":"deeprl"},{"id":"2506.05716","title":"Ensemble Elastic DQN: A Step Dependent Ensemble Approach for Reducing Overestimation in Deep Value-Based Reinforcement Learning","created":"2025-06-06","cited_by_count":0,"area":"deeprl"},{"id":"2509.04815","title":"An Arbitration Control for an Ensemble of Diversified DQN variants in Continual Reinforcement Learning","created":"2025-09-05","cited_by_count":0,"area":"deeprl"},{"id":"2510.01083","title":"Multi-Actor Multi-Critic Deep Deterministic Reinforcement Learning with a Novel Q-Ensemble Method","created":"2025-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2512.10492","title":"UACER: An Uncertainty-Adaptive Critic Ensemble Framework for Robust Adversarial Reinforcement Learning","created":"2025-12-11","cited_by_count":0,"area":"deeprl"},{"id":"2512.17034","title":"GB-DQN: Gradient Boosted DQN Models for Non-stationary Reinforcement Learning","created":"2025-12-18","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}