{"total":204,"rows":[{"id":"2212.03238","title":"Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior","created":"2022-12-06","cited_by_count":138,"area":null},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102,"area":null},{"id":"2401.10034","title":"Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap","created":"2024-01-18","cited_by_count":90,"area":null},{"id":"2306.01102","title":"LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization","created":"2023-06-01","cited_by_count":87,"area":null},{"id":"2106.03894","title":"Differentiable Quality Diversity","created":"2021-06-07","cited_by_count":72,"area":null},{"id":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63,"area":null},{"id":"2206.04199","title":"Deep Surrogate Assisted Generation of Environments","created":"2022-06-09","cited_by_count":40,"area":null},{"id":"2103.07927","title":"Modelling Behavioural Diversity for Learning in Open-Ended Games","created":"2021-03-14","cited_by_count":39,"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":"2107.08981","title":"Hierarchical Few-Shot Imitation with Skill Transition Models","created":"2021-07-19","cited_by_count":37,"area":null},{"id":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37,"area":null},{"id":"2302.01605","title":"Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased","created":"2023-02-03","cited_by_count":37,"area":null},{"id":"2308.14284","title":"Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning","created":"2023-08-28","cited_by_count":36,"area":null},{"id":"2103.04564","title":"Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization","created":"2021-03-08","cited_by_count":35,"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":"2206.07505","title":"Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2106.05648","title":"Unsupervised Behaviour Discovery with Quality-Diversity Optimisation","created":"2021-06-10","cited_by_count":30,"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":"2303.04150","title":"Evolutionary Reinforcement Learning: A Survey","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2111.06956","title":"Human irrationality: both bad and good for reward inference","created":"2021-11-12","cited_by_count":25,"area":null},{"id":"2205.10752","title":"Covariance Matrix Adaptation MAP-Annealing","created":"2022-05-22","cited_by_count":25,"area":null},{"id":"2102.07659","title":"Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems","created":"2021-02-15","cited_by_count":24,"area":null},{"id":"2204.02246","title":"Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization","created":"2022-04-04","cited_by_count":23,"area":null},{"id":"2210.03516","title":"Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery","created":"2022-10-06","cited_by_count":23,"area":null},{"id":"2205.14090","title":"Surrogate modeling for Bayesian optimization beyond a single Gaussian process","created":"2022-05-27","cited_by_count":22,"area":null},{"id":"2104.13424","title":"Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution","created":"2021-04-27","cited_by_count":20,"area":null},{"id":"2109.08522","title":"Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoires","created":"2021-09-16","cited_by_count":20,"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":"2103.07084","title":"Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information","created":"2021-03-12","cited_by_count":19,"area":null},{"id":"2202.03057","title":"Multi-Objective Quality Diversity Optimization","created":"2022-02-07","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":"2305.06436","title":"Multi-Robot Coordination and Layout Design for Automated Warehousing","created":"2023-05-10","cited_by_count":17,"area":null},{"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":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2304.11787","title":"B2Opt: Learning to Optimize Black-box Optimization with Little Budget","created":"2023-04-24","cited_by_count":15,"area":null},{"id":"2306.16884","title":"Policy Space Diversity for Non-Transitive Games","created":"2023-06-29","cited_by_count":15,"area":null},{"id":"2308.09175","title":"Diversifying AI: Towards Creative Chess with AlphaZero","created":"2023-08-17","cited_by_count":15,"area":null},{"id":"2202.01258","title":"Accelerated Quality-Diversity through Massive Parallelism","created":"2022-02-02","cited_by_count":14,"area":null},{"id":"2306.00087","title":"Adaptive Coordination in Social Embodied Rearrangement","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2403.06966","title":"Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts","created":"2024-03-11","cited_by_count":14,"area":"moe"},{"id":"2102.03140","title":"Sparse Reward Exploration via Novelty Search and Emitters","created":"2021-02-05","cited_by_count":13,"area":null},{"id":"2403.09930","title":"Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics","created":"2024-03-15","cited_by_count":13,"area":"deeprl"},{"id":"2208.04957","title":"Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution","created":"2022-08-09","cited_by_count":12,"area":null},{"id":"2210.12719","title":"Learning General World Models in a Handful of Reward-Free Deployments","created":"2022-10-23","cited_by_count":12,"area":"wm"},{"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":"2601.07821","title":"Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation","created":"2026-01-12","cited_by_count":11,"area":"offlinerl"},{"id":"2201.13248","title":"SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation","created":"2022-01-27","cited_by_count":10,"area":null},{"id":"2207.13224","title":"PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations","created":"2022-07-27","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":"2303.16207","title":"The Quality-Diversity Transformer: Generating Behavior-Conditioned Trajectories with Decision Transformers","created":"2023-03-27","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":"2205.08189","title":"Automatic Acquisition of a Repertoire of Diverse Grasping Trajectories through Behavior Shaping and Novelty Search","created":"2022-05-17","cited_by_count":9,"area":null},{"id":"2310.18622","title":"Arbitrarily Scalable Environment Generators via Neural Cellular Automata","created":"2023-10-28","cited_by_count":9,"area":null},{"id":"2410.06084","title":"Diversity-Rewarded CFG Distillation","created":"2024-10-08","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":"2109.06826","title":"Few-shot Quality-Diversity Optimization","created":"2021-09-14","cited_by_count":8,"area":null},{"id":"2112.14570","title":"Lyapunov Exponents for Diversity in Differentiable Games","created":"2021-12-24","cited_by_count":8,"area":null},{"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":"2307.08364","title":"Q(D)O-ES: Population-based Quality (Diversity) Optimisation for Post Hoc Ensemble Selection in AutoML","created":"2023-07-17","cited_by_count":8,"area":null},{"id":"2311.01059","title":"Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2411.05614","title":"Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey","created":"2024-11-08","cited_by_count":8,"area":"deeprl"},{"id":"2105.04247","title":"Expressivity of Parameterized and Data-driven Representations in Quality Diversity Search","created":"2021-05-10","cited_by_count":7,"area":null},{"id":"2110.00704","title":"OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation","created":"2021-10-02","cited_by_count":7,"area":null},{"id":"2201.04286","title":"Evolutionary Action Selection for Gradient-based Policy Learning","created":"2022-01-12","cited_by_count":7,"area":null},{"id":"2204.03655","title":"Learning to Walk Autonomously via Reset-Free Quality-Diversity","created":"2022-04-07","cited_by_count":7,"area":null},{"id":"2208.12758","title":"Quality Diversity Evolutionary Learning of Decision Trees","created":"2022-08-17","cited_by_count":7,"area":null},{"id":"2210.09918","title":"Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity","created":"2022-10-18","cited_by_count":7,"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":"2107.07844","title":"Versatile modular neural locomotion control with fast learning","created":"2021-07-16","cited_by_count":6,"area":null},{"id":"2203.10941","title":"Transfer Dynamics in Emergent Evolutionary Curricula","created":"2022-03-03","cited_by_count":6,"area":null},{"id":"2303.06164","title":"Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning","created":"2023-03-10","cited_by_count":6,"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":"2602.15951","title":"MadEvolve: Evolutionary Optimization of Cosmological Algorithms with Large Language Models","created":"2026-02-17","cited_by_count":6,"area":null},{"id":"2111.01919","title":"Discovering and Exploiting Sparse Rewards in a Learned Behavior Space","created":"2021-11-02","cited_by_count":5,"area":null},{"id":"2204.05726","title":"Hierarchical Quality-Diversity for Online Damage Recovery","created":"2022-04-12","cited_by_count":5,"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":"2310.06648","title":"Diversity from Human Feedback","created":"2023-10-10","cited_by_count":5,"area":"alignment"},{"id":"2403.17164","title":"Multi-Objective Quality-Diversity for Crystal Structure Prediction","created":"2024-03-25","cited_by_count":5,"area":null},{"id":"2106.01741","title":"Lifetime policy reuse and the importance of task capacity","created":"2021-06-03","cited_by_count":4,"area":null},{"id":"2110.06912","title":"OPEn: An Open-ended Physics Environment for Learning Without a Task","created":"2021-10-13","cited_by_count":4,"area":null},{"id":"2112.00600","title":"Towards Futuristic Autonomous Experimentation--A Surprise-Reacting Sequential Experiment Policy","created":"2021-12-01","cited_by_count":4,"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":"2206.06674","title":"Severe Damage Recovery in Evolving Soft Robots through Differentiable Programming","created":"2022-06-14","cited_by_count":4,"area":null},{"id":"2210.02260","title":"From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems","created":"2022-10-05","cited_by_count":4,"area":null},{"id":"2211.13742","title":"Assessing Quality-Diversity Neuro-Evolution Algorithms Performance in Hard Exploration Problems","created":"2022-11-24","cited_by_count":4,"area":null},{"id":"2302.00782","title":"Evolving Flying Machines in Minecraft Using Quality Diversity","created":"2023-02-01","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":"2307.16890","title":"Discovering Adaptable Symbolic Algorithms from Scratch","created":"2023-07-31","cited_by_count":4,"area":null},{"id":"2311.01829","title":"Mix-ME: Quality-Diversity for Multi-Agent Learning","created":"2023-11-03","cited_by_count":4,"area":null},{"id":"2401.13460","title":"Multi-Agent Diagnostics for Robustness via Illuminated Diversity","created":"2024-01-24","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":"2503.08394","title":"($\\theta_l, \\theta_u$)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2105.04252","title":"An Analysis of Phenotypic Diversity in Multi-Solution Optimization","created":"2021-05-10","cited_by_count":3,"area":null},{"id":"2105.08484","title":"Fast Game Content Adaptation Through Bayesian-based Player Modelling","created":"2021-05-18","cited_by_count":3,"area":null},{"id":"2210.11442","title":"Augmentative Topology Agents For Open-Ended Learning","created":"2022-10-20","cited_by_count":3,"area":null},{"id":"2302.13360","title":"Guiding the Sequential Experiments in Autonomous Experimentation Platforms through EI-based Bayesian Optimization and Bayesian Model Averaging","created":"2023-02-26","cited_by_count":3,"area":null}],"next_cursor":"100"}