{"total":72,"rows":[{"id":"2311.16822","title":"Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop","created":"2023-11-28","cited_by_count":79,"area":null},{"id":"2206.04199","title":"Deep Surrogate Assisted Generation of Environments","created":"2022-06-09","cited_by_count":40,"area":null},{"id":"2202.03666","title":"Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning","created":"2022-02-08","cited_by_count":38,"area":null},{"id":"2106.10853","title":"On the Importance of Environments in Human-Robot Coordination","created":"2021-06-21","cited_by_count":37,"area":null},{"id":"2109.05489","title":"Illuminating Diverse Neural Cellular Automata for Level Generation","created":"2021-09-12","cited_by_count":35,"area":null},{"id":"2303.00191","title":"pyribs: A Bare-Bones Python Library for Quality Diversity Optimization","created":"2023-03-01","cited_by_count":30,"area":null},{"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":"2205.10752","title":"Covariance Matrix Adaptation MAP-Annealing","created":"2022-05-22","cited_by_count":25,"area":null},{"id":"2305.13795","title":"Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning","created":"2023-05-23","cited_by_count":20,"area":null},{"id":"2202.03057","title":"Multi-Objective Quality Diversity Optimization","created":"2022-02-07","cited_by_count":19,"area":null},{"id":"2207.09684","title":"On the Versatile Uses of Partial Distance Correlation in Deep Learning","created":"2022-07-20","cited_by_count":19,"area":null},{"id":"2305.18738","title":"Generating Behaviorally Diverse Policies with Latent Diffusion Models","created":"2023-05-30","cited_by_count":19,"area":"diffusion"},{"id":"2308.03665","title":"QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration","created":"2023-08-07","cited_by_count":17,"area":null},{"id":"2202.01258","title":"Accelerated Quality-Diversity through Massive Parallelism","created":"2022-02-02","cited_by_count":14,"area":null},{"id":"2210.17375","title":"ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation","created":"2022-10-26","cited_by_count":14,"area":null},{"id":"2603.12440","title":"KernelFoundry: Hardware-aware evolutionary GPU kernel optimization","created":"2026-03-12","cited_by_count":13,"area":null},{"id":"2403.13208","title":"CaDRE: Controllable and Diverse Generation of Safety-Critical Driving Scenarios using Real-World Trajectories","created":"2024-03-19","cited_by_count":11,"area":"driving"},{"id":"2202.02163","title":"COIL: Constrained Optimization in Learned Latent Space: Learning Representations for Valid Solutions","created":"2022-02-04","cited_by_count":10,"area":null},{"id":"2210.02622","title":"Training Diverse High-Dimensional Controllers by Scaling Covariance Matrix Adaptation MAP-Annealing","created":"2022-10-06","cited_by_count":10,"area":null},{"id":"2211.02193","title":"Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning","created":"2022-11-04","cited_by_count":10,"area":null},{"id":"2310.12103","title":"Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization","created":"2023-10-18","cited_by_count":10,"area":"alignment"},{"id":"2310.18622","title":"Arbitrarily Scalable Environment Generators via Neural Cellular Automata","created":"2023-10-28","cited_by_count":9,"area":null},{"id":"2506.07121","title":"Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models","created":"2025-06-08","cited_by_count":9,"area":"safety"},{"id":"2204.09828","title":"Relevance-guided Unsupervised Discovery of Abilities with Quality-Diversity Algorithms","created":"2022-04-21","cited_by_count":8,"area":null},{"id":"2304.13787","title":"Surrogate Assisted Generation of Human-Robot Interaction Scenarios","created":"2023-04-26","cited_by_count":8,"area":null},{"id":"2404.15794","title":"Large Language Models as In-context AI Generators for Quality-Diversity","created":"2024-04-24","cited_by_count":7,"area":null},{"id":"2308.05483","title":"Quality Diversity under Sparse Reward and Sparse Interaction: Application to Grasping in Robotics","created":"2023-08-10","cited_by_count":6,"area":null},{"id":"2401.08632","title":"Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning","created":"2023-12-10","cited_by_count":6,"area":null},{"id":"2303.12803","title":"Evolving Populations of Diverse RL Agents with MAP-Elites","created":"2023-03-09","cited_by_count":5,"area":null},{"id":"2306.09309","title":"Who Needs to Know? Minimal Knowledge for Optimal Coordination","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2310.06648","title":"Diversity from Human Feedback","created":"2023-10-10","cited_by_count":5,"area":"alignment"},{"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":"2403.17164","title":"Multi-Objective Quality-Diversity for Crystal Structure Prediction","created":"2024-03-25","cited_by_count":5,"area":null},{"id":"2202.08376","title":"How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity","created":"2022-02-16","cited_by_count":4,"area":null},{"id":"2305.16148","title":"Leveraging Human Feedback to Evolve and Discover Novel Emergent Behaviors in Robot Swarms","created":"2023-04-25","cited_by_count":4,"area":null},{"id":"2306.05138","title":"Gradient-Informed Quality Diversity for the Illumination of Discrete Spaces","created":"2023-06-08","cited_by_count":4,"area":null},{"id":"2402.01275","title":"Parametric-Task MAP-Elites","created":"2024-02-02","cited_by_count":4,"area":null},{"id":"2410.06151","title":"Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity","created":"2024-10-08","cited_by_count":4,"area":"offlinerl"},{"id":"2411.06965","title":"Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration","created":"2024-11-11","cited_by_count":4,"area":"offlinerl"},{"id":"2204.14061","title":"A Collection of Quality Diversity Optimization Problems Derived from Hyperparameter Optimization of Machine Learning Models","created":"2022-04-28","cited_by_count":3,"area":null},{"id":"2304.03672","title":"Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains","created":"2023-04-07","cited_by_count":3,"area":null},{"id":"2305.08042","title":"CHSEL: Producing Diverse Plausible Pose Estimates from Contact and Free Space Data","created":"2023-05-14","cited_by_count":3,"area":null},{"id":"2411.04466","title":"Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity","created":"2024-11-07","cited_by_count":3,"area":"deeprl"},{"id":"2504.15457","title":"Improving Human-AI Coordination through Online Adversarial Training and Generative Models","created":"2025-04-21","cited_by_count":3,"area":null},{"id":"2506.05634","title":"AutoQD: Automatic Discovery of Diverse Behaviors with Quality-Diversity Optimization","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2302.12668","title":"Improving the Data Efficiency of Multi-Objective Quality-Diversity through Gradient Assistance and Crowding Exploration","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2303.06137","title":"Enhancing MAP-Elites with Multiple Parallel Evolution Strategies","created":"2023-03-10","cited_by_count":2,"area":null},{"id":"2310.00301","title":"Enhancing the Hierarchical Environment Design via Generative Trajectory Modeling","created":"2023-09-30","cited_by_count":2,"area":null},{"id":"2312.11331","title":"Density Descent for Diversity Optimization","created":"2023-12-18","cited_by_count":2,"area":null},{"id":"2503.11126","title":"MUSS: Multilevel Subset Selection for Relevance and Diversity","created":"2025-03-14","cited_by_count":2,"area":"rag"},{"id":"2504.03715","title":"Multi-Objective Quality-Diversity in Unstructured and Unbounded Spaces","created":"2025-03-28","cited_by_count":2,"area":null},{"id":"2505.22275","title":"Full Domain Analysis in Fluid Dynamics","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2206.09743","title":"Guided Safe Shooting: model based reinforcement learning with safety constraints","created":"2022-06-20","cited_by_count":1,"area":null},{"id":"2310.10610","title":"Quantifying Assistive Robustness Via the Natural-Adversarial Frontier","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2406.03731","title":"Quality-Diversity with Limited Resources","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2407.17515","title":"Quality Diversity for Robot Learning: Limitations and Future Directions","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2409.04711","title":"Algorithmic Scenario Generation as Quality Diversity Optimization","created":"2024-09-07","cited_by_count":1,"area":null},{"id":"2411.12433","title":"Preference-Conditioned Gradient Variations for Multi-Objective Quality-Diversity","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2504.03991","title":"Algorithmic Prompt Generation for Diverse Human-like Teaming and Communication with Large Language Models","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2512.00810","title":"Soft Quality-Diversity Optimization","created":"2025-11-30","cited_by_count":1,"area":null},{"id":"2601.01082","title":"Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces","created":"2026-01-03","cited_by_count":1,"area":null},{"id":"2603.23738","title":"BXRL: Behavior-Explainable Reinforcement Learning","created":"2026-03-24","cited_by_count":1,"area":"deeprl"},{"id":"2605.27130","title":"DEI: Diversity in Evolutionary Inference for Quality-Diversity Search","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2607.22375","title":"IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation","created":"2026-07-24","cited_by_count":1,"area":"agents"},{"id":"2406.13711","title":"Imagining In-distribution States: How Predictable Robot Behavior Can Enable User Control Over Learned Policies","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2408.16776","title":"Online Behavior Modification for Expressive User Control of RL-Trained Robots","created":"2024-08-15","cited_by_count":0,"area":"deeprl"},{"id":"2412.14085","title":"Future Research Avenues for Artificial Intelligence in Digital Gaming: An Exploratory Report","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2602.00478","title":"Quality-Diversity Optimization as Multi-Objective Optimization","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.09813","title":"Efficient Unsupervised Environment Design through Hierarchical Policy Representation Learning","created":"2026-02-10","cited_by_count":0,"area":"distill"},{"id":"2605.09781","title":"Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2606.04658","title":"U-Net-Accelerated Quality-Diversity Optimization for Climate-Adaptive Urban Layouts","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2610.15724","title":"Uncovering the Generative Landscape of Diffusion Models: A Spectral-Guided Quality-Diversity Diffusion Framework","created":"2026-10-11","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}