{"total":56,"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":"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":"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":"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":"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":"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":"2303.02618","title":"Ensemble Reinforcement Learning: A Survey","created":"2023-03-05","cited_by_count":16,"area":null},{"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":"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":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"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":"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":"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":"2311.18393","title":"Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control","created":"2023-11-30","cited_by_count":4,"area":null},{"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":"2501.12739","title":"Multiscale Training of Convolutional Neural Networks","created":"2025-01-22","cited_by_count":3,"area":null},{"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":"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":"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":"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":"2512.24325","title":"MaRCA: Multi-Agent Reinforcement Learning for Dynamic Computation Allocation in Large-Scale Recommender Systems","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2607.19397","title":"Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning","created":"2026-07-04","cited_by_count":0,"area":null}],"next_cursor":null}