{"total":81,"rows":[{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"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":"2209.03302","title":"Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?","created":"2022-09-07","cited_by_count":125,"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":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"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":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49,"area":null},{"id":"2306.17693","title":"Thompson sampling for improved exploration in GFlowNets","created":"2023-06-30","cited_by_count":32,"area":null},{"id":"2103.00445","title":"Ensemble Bootstrapping for Q-Learning","created":"2021-02-28","cited_by_count":31,"area":null},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"area":null},{"id":"2201.01666","title":"Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation","created":"2022-01-05","cited_by_count":27,"area":null},{"id":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"area":null},{"id":"2105.07253","title":"Regret Minimization Experience Replay in Off-Policy Reinforcement Learning","created":"2021-05-15","cited_by_count":25,"area":null},{"id":"2310.17634","title":"Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion","created":"2023-10-26","cited_by_count":24,"area":null},{"id":"2305.18258","title":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2206.04672","title":"Overcoming the Spectral Bias of Neural Value Approximation","created":"2022-06-09","cited_by_count":19,"area":null},{"id":"2107.01825","title":"Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation","created":"2021-07-05","cited_by_count":18,"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":"2205.15460","title":"Critic Sequential Monte Carlo","created":"2022-05-30","cited_by_count":16,"area":null},{"id":"2204.04905","title":"Evaluating Vision Transformer Methods for Deep Reinforcement Learning from Pixels","created":"2022-04-11","cited_by_count":13,"area":null},{"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":"2103.02886","title":"Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings","created":"2021-03-04","cited_by_count":12,"area":null},{"id":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","cited_by_count":12,"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":"2206.11996","title":"The Real Deal: A Review of Challenges and Opportunities in Moving Reinforcement Learning-Based Traffic Signal Control Systems Towards Reality","created":"2022-06-23","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":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2111.15382","title":"Continuous Control With Ensemble Deep Deterministic Policy Gradients","created":"2021-11-30","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":"2210.04642","title":"Exploration via Planning for Information about the Optimal Trajectory","created":"2022-10-06","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":"2210.13455","title":"Epistemic Monte Carlo Tree Search","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2302.10145","title":"Improving Deep Policy Gradients with Value Function Search","created":"2023-02-20","cited_by_count":7,"area":null},{"id":"2309.12038","title":"Uncertainty-driven Exploration Strategies for Online Grasp Learning","created":"2023-09-21","cited_by_count":6,"area":null},{"id":"2310.19527","title":"On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics","created":"2023-10-30","cited_by_count":6,"area":null},{"id":"2106.08918","title":"Towards Automatic Actor-Critic Solutions to Continuous Control","created":"2021-06-16","cited_by_count":5,"area":null},{"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":"2110.03155","title":"Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning","created":"2021-10-07","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":"2303.02378","title":"Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control","created":"2023-03-04","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":"2507.09041","title":"Behavioral Exploration: Learning to Explore via In-Context Adaptation","created":"2025-07-11","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":"2111.12045","title":"Adaptive Multi-Goal Exploration","created":"2021-11-23","cited_by_count":4,"area":null},{"id":"2305.13185","title":"Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice","created":"2023-05-22","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":"2312.10289","title":"Active Reinforcement Learning for Robust Building Control","created":"2023-12-16","cited_by_count":4,"area":null},{"id":"2205.09117","title":"Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks","created":"2022-05-18","cited_by_count":3,"area":null},{"id":"2205.10416","title":"ARLO: A Framework for Automated Reinforcement Learning","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2207.13730","title":"Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control","created":"2022-07-27","cited_by_count":3,"area":null},{"id":"2210.03649","title":"How to Enable Uncertainty Estimation in Proximal Policy Optimization","created":"2022-10-07","cited_by_count":3,"area":null},{"id":"2303.02557","title":"Bounding the Optimal Value Function in Compositional Reinforcement Learning","created":"2023-03-05","cited_by_count":3,"area":null},{"id":"2312.04386","title":"Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2406.10775","title":"A Rate-Distortion View of Uncertainty Quantification","created":"2024-06-16","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":"2110.14818","title":"Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates","created":"2021-10-28","cited_by_count":2,"area":null},{"id":"2209.12412","title":"DEFT: Diverse Ensembles for Fast Transfer in Reinforcement Learning","created":"2022-09-26","cited_by_count":2,"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":"2208.13125","title":"Normality-Guided Distributional Reinforcement Learning for Continuous Control","created":"2022-08-28","cited_by_count":1,"area":null},{"id":"2209.14488","title":"Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2211.15205","title":"CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2506.02841","title":"Ensemble-MIX: Enhancing Sample-Efficiency in Multi-Agent RL via Selective Ensemble-Based Exploration","created":"2025-06-03","cited_by_count":1,"area":null},{"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":"2509.03219","title":"A Novel Framework for Uncertainty-Driven Adaptive Exploration","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2606.19656","title":"DF-ExpEnse: Diffusion Filtered Exploration for Sample Efficient Finetuning","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2110.12081","title":"Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction","created":"2021-10-22","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":"2205.15064","title":"SEREN: Knowing When to Explore and When to Exploit","created":"2022-05-30","cited_by_count":0,"area":null},{"id":"2302.09676","title":"Leveraging Prior Knowledge in Reinforcement Learning via Double-Sided Bounds on the Value Function","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2305.11017","title":"Deep Metric Tensor Regularized Policy Gradient","created":"2023-05-18","cited_by_count":0,"area":null},{"id":"2305.19344","title":"infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-information","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2307.06501","title":"Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning","created":"2023-07-13","cited_by_count":0,"area":null},{"id":"2310.01827","title":"Learning and reusing primitive behaviours to improve Hindsight Experience Replay sample efficiency","created":"2023-10-03","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":"2405.08252","title":"Smart Sampling: Self-Attention and Bootstrapping for Improved Ensembled Q-Learning","created":"2024-05-14","cited_by_count":0,"area":null},{"id":"2503.11964","title":"Entropy-regularized Gradient Estimators for Approximate Bayesian Inference","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2607.06776","title":"Efficient Bayesian Deep Ensembles via Analytic Predictive Inference","created":"2026-07-07","cited_by_count":0,"area":null}],"next_cursor":null}