{"total":79,"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":"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":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"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":"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":"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":"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":"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":"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":"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":"2409.11702","title":"Discovering Conceptual Knowledge with Analytic Ontology Templates for Articulated Objects","created":"2024-09-18","cited_by_count":5,"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":"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":"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":"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":"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":"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":"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":"2502.02382","title":"Circular Microalgae-Based Carbon Control for Net Zero","created":"2025-02-04","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":"2508.11514","title":"DiCriTest: Testing Scenario Generation for Decision-Making Agents Considering Diversity and Criticality","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2606.06041","title":"Sample-efficient Low-level Motion Planning for Robotic Manipulation Tasks via Zero-shot Transfer Learning","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2107.03741","title":"Adaptation of Quadruped Robot Locomotion with Meta-Learning","created":"2021-07-08","cited_by_count":0,"area":null},{"id":"2109.05604","title":"Direct Random Search for Fine Tuning of Deep Reinforcement Learning Policies","created":"2021-09-12","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":"2212.14262","title":"Invariance to Quantile Selection in Distributional Continuous Control","created":"2022-12-29","cited_by_count":0,"area":null},{"id":"2301.11168","title":"Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2303.04944","title":"On the Benefits of Biophysical Synapses","created":"2023-03-08","cited_by_count":0,"area":null},{"id":"2304.01096","title":"Evolving Artificial Neural Networks To Imitate Human Behaviour In Shinobi III : Return of the Ninja Master","created":"2023-04-03","cited_by_count":0,"area":null},{"id":"2304.12431","title":"Neuroevolution of Recurrent Architectures on Control Tasks","created":"2023-04-03","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":"2308.01759","title":"Bag of Policies for Distributional Deep Exploration","created":"2023-08-03","cited_by_count":0,"area":null},{"id":"2311.17565","title":"Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning","created":"2023-11-29","cited_by_count":0,"area":null},{"id":"2502.18447","title":"Supervised Reward Inference","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2507.04309","title":"Domain Adaptation of Drag Reduction Policy to Partial Measurements","created":"2025-07-06","cited_by_count":0,"area":null},{"id":"2509.12716","title":"Joint AoI and Handover Optimization in Space-Air-Ground Integrated Network","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2603.00104","title":"Alpha-RF: Automated RF-Filter-Circuit Design with Neural Simulator and Reinforcement Learning","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.26687","title":"Learning Energy-Efficient Air--Ground Actuation for Hybrid Robots on Stair-Like Terrain","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2606.02614","title":"Margin Play: A Multi-Agent System For Public Policy Analysis In The Brazilian Equatorial Margin","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2609.20404","title":"Learning Principal-Agent Contracts for Equitable Smallholder Carbon Farming under Moral Hazard and Adverse Selection","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}