{"total":165,"rows":[{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293,"area":"offlinerl"},{"id":"2304.10573","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","created":"2023-04-20","cited_by_count":325,"area":"diffusion"},{"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":"2202.08432","title":"AKB-48: A Real-World Articulated Object Knowledge Base","created":"2022-02-17","cited_by_count":82,"area":null},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2409.10164","title":"Quantile Regression for Distributional Reward Models in RLHF","created":"2024-09-16","cited_by_count":60,"area":"alignment"},{"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":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"id":"2402.04764","title":"Code as Reward: Empowering Reinforcement Learning with VLMs","created":"2024-02-07","cited_by_count":39,"area":"mllm"},{"id":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38,"area":"deeprl"},{"id":"2401.09750","title":"Exploration and Anti-Exploration with Distributional Random Network Distillation","created":"2024-01-18","cited_by_count":33,"area":"deeprl"},{"id":"2102.09225","title":"Continuous Doubly Constrained Batch Reinforcement Learning","created":"2021-02-18","cited_by_count":27,"area":"offlinerl"},{"id":"2401.11963","title":"Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms","created":"2024-01-22","cited_by_count":26,"area":"deeprl"},{"id":"2103.06469","title":"Generalizable Episodic Memory for Deep Reinforcement Learning","created":"2021-03-11","cited_by_count":23,"area":null},{"id":"2112.10504","title":"Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic","created":"2021-12-16","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":"2301.10923","title":"Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints","created":"2023-01-26","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":"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":"2105.11366","title":"GMAC: A Distributional Perspective on Actor-Critic Framework","created":"2021-05-24","cited_by_count":16,"area":null},{"id":"2210.15479","title":"Low-Rank Modular Reinforcement Learning via Muscle Synergy","created":"2022-10-26","cited_by_count":16,"area":null},{"id":"2301.12130","title":"Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning","created":"2023-01-28","cited_by_count":16,"area":"offlinerl"},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2411.18562","title":"DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation","created":"2024-11-27","cited_by_count":15,"area":null},{"id":"2210.07432","title":"Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations","created":"2022-10-14","cited_by_count":14,"area":null},{"id":"2309.14246","title":"Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2305.12751","title":"Testing of Deep Reinforcement Learning Agents with Surrogate Models","created":"2023-05-22","cited_by_count":13,"area":null},{"id":"2112.02807","title":"MDPFuzz: Testing Models Solving Markov Decision Processes","created":"2021-12-06","cited_by_count":12,"area":null},{"id":"2205.10047","title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure","created":"2022-05-20","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":"2202.09673","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","created":"2022-02-19","cited_by_count":11,"area":"offlinerl"},{"id":"2504.07095","title":"Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning","created":"2025-04-09","cited_by_count":11,"area":"wm"},{"id":"2206.06841","title":"Robust Reinforcement Learning with Distributional Risk-averse formulation","created":"2022-06-14","cited_by_count":10,"area":null},{"id":"2211.15034","title":"Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probability","created":"2022-11-28","cited_by_count":9,"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":"2306.07124","title":"Diverse Projection Ensembles for Distributional Reinforcement Learning","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2310.13396","title":"RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup","created":"2023-10-20","cited_by_count":8,"area":null},{"id":"2411.00465","title":"Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions","created":"2024-11-01","cited_by_count":8,"area":"offlinerl"},{"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":"2403.11062","title":"A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization","created":"2024-03-17","cited_by_count":7,"area":"deeprl"},{"id":"2411.01894","title":"Efficient Active Imitation Learning with Random Network Distillation","created":"2024-11-04","cited_by_count":7,"area":"offlinerl"},{"id":"2111.12673","title":"Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning","created":"2021-11-24","cited_by_count":6,"area":null},{"id":"2112.11216","title":"Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients","created":"2021-12-21","cited_by_count":6,"area":null},{"id":"2204.09424","title":"SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2208.00818","title":"Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning","created":"2022-08-01","cited_by_count":6,"area":null},{"id":"2211.04786","title":"Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration","created":"2022-11-09","cited_by_count":6,"area":null},{"id":"2309.03208","title":"A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design","created":"2023-08-22","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":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"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":"2308.06590","title":"Value-Distributional Model-Based Reinforcement Learning","created":"2023-08-12","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":"2403.00282","title":"Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning","created":"2024-03-01","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":"2409.11702","title":"Discovering Conceptual Knowledge with Analytic Ontology Templates for Articulated Objects","created":"2024-09-18","cited_by_count":5,"area":null},{"id":"2410.07686","title":"The Power of Input: Benchmarking Zero-Shot Sim-To-Real Transfer of Reinforcement Learning Control Policies for Quadrotor Control","created":"2024-10-10","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":"2306.03530","title":"RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control","created":"2023-06-06","cited_by_count":4,"area":null},{"id":"2410.20312","title":"Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model","created":"2024-10-27","cited_by_count":4,"area":"offlinerl"},{"id":"2602.10539","title":"What Makes Value Learning Efficient in Residual Reinforcement Learning?","created":"2026-02-11","cited_by_count":4,"area":"deeprl"},{"id":"2102.04307","title":"Learning Optimal Strategies for Temporal Tasks in Stochastic Games","created":"2021-02-08","cited_by_count":3,"area":null},{"id":"2103.11265","title":"Bayesian Distributional Policy Gradients","created":"2021-03-20","cited_by_count":3,"area":null},{"id":"2109.11867","title":"The $f$-Divergence Reinforcement Learning Framework","created":"2021-09-24","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":"2207.13730","title":"Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control","created":"2022-07-27","cited_by_count":3,"area":null},{"id":"2405.07004","title":"Stealthy Imitation: Reward-guided Environment-free Policy Stealing","created":"2024-05-11","cited_by_count":3,"area":"alignment"},{"id":"2407.02231","title":"Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approach","created":"2024-07-02","cited_by_count":3,"area":"deeprl"},{"id":"2408.16118","title":"RAIN: Reinforcement Algorithms for Improving Numerical Weather and Climate Models","created":"2024-08-28","cited_by_count":3,"area":"deeprl"},{"id":"2501.17431","title":"Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment","created":"2025-01-29","cited_by_count":3,"area":"alignment"},{"id":"2603.14469","title":"Physics-Informed Policy Optimization via Analytic Dynamics Regularization","created":"2026-03-15","cited_by_count":3,"area":"deeprl"},{"id":"2110.13523","title":"Automating Control of Overestimation Bias for Reinforcement Learning","created":"2021-10-26","cited_by_count":2,"area":null},{"id":"2208.02809","title":"The Role of Morphological Variation in Evolutionary Robotics: Maximizing Performance and Robustness","created":"2022-08-04","cited_by_count":2,"area":null},{"id":"2306.06637","title":"PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm","created":"2023-06-11","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":"2307.16152","title":"Variance Control for Distributional Reinforcement Learning","created":"2023-07-30","cited_by_count":2,"area":null},{"id":"2401.09034","title":"UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender Systems","created":"2024-01-17","cited_by_count":2,"area":"deeprl"},{"id":"2405.15421","title":"Model-free reinforcement learning with noisy actions for automated experimental control in optics","created":"2024-05-24","cited_by_count":2,"area":"deeprl"},{"id":"2410.06347","title":"Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning","created":"2024-10-08","cited_by_count":2,"area":"offlinerl"},{"id":"2412.06684","title":"Exploring Critical Testing Scenarios for Decision-Making Policies: An LLM Approach","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2412.07477","title":"Progressive-Resolution Policy Distillation: Leveraging Coarse-Resolution Simulations for Time-Efficient Fine-Resolution Policy Learning","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2506.06954","title":"Safety-Aware Reinforcement Learning for Control via Risk-Sensitive Action-Value Iteration and Quantile Regression","created":"2025-06-08","cited_by_count":2,"area":"deeprl"},{"id":"2602.11800","title":"Temporal Difference Learning with Constrained Initial Representations","created":"2026-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2603.23889","title":"Off-Policy Safe Reinforcement Learning with Constrained Optimistic Exploration","created":"2026-03-25","cited_by_count":2,"area":"deeprl"},{"id":"2607.15003","title":"SMC-ES: Automated synthesis of formally verified control policies","created":"2026-07-16","cited_by_count":2,"area":"deeprl"},{"id":"2110.09712","title":"Balancing Value Underestimation and Overestimation with Realistic Actor-Critic","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2206.12674","title":"Guided Exploration in Reinforcement Learning via Monte Carlo Critic Optimization","created":"2022-06-25","cited_by_count":1,"area":null},{"id":"2209.07171","title":"Learning to Exploit Elastic Actuators for Quadruped Locomotion","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2209.14875","title":"Accelerating Laboratory Automation Through Robot Skill Learning For Sample Scraping","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2301.01298","title":"Contextual Conservative Q-Learning for Offline Reinforcement Learning","created":"2023-01-03","cited_by_count":1,"area":"offlinerl"},{"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":"2311.05084","title":"Signal Temporal Logic-Guided Apprenticeship Learning","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2401.05251","title":"ReACT: Reinforcement Learning for Controller Parametrization using B-Spline Geometries","created":"2024-01-10","cited_by_count":1,"area":"deeprl"},{"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":"2404.10632","title":"Compact Multi-Object Placement Using Adjacency-Aware Reinforcement Learning","created":"2024-04-16","cited_by_count":1,"area":"deeprl"},{"id":"2404.15617","title":"A Differential and Pointwise Control Approach to Reinforcement Learning","created":"2024-04-24","cited_by_count":1,"area":"deeprl"},{"id":"2404.16159","title":"AFU: Actor-Free critic Updates in off-policy RL for continuous control","created":"2024-04-24","cited_by_count":1,"area":"deeprl"}],"next_cursor":"100"}