{"total":88,"rows":[{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2106.03894","title":"Differentiable Quality Diversity","created":"2021-06-07","cited_by_count":72,"area":null},{"id":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2210.03475","title":"Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization","created":"2022-10-07","cited_by_count":58,"area":null},{"id":"2102.03765","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","created":"2021-02-07","cited_by_count":55,"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":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37,"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":"2303.04150","title":"Evolutionary Reinforcement Learning: A Survey","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"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":"2204.13998","title":"Learning High-DOF Reaching-and-Grasping via Dynamic Representation of Gripper-Object Interaction","created":"2022-04-03","cited_by_count":24,"area":null},{"id":"2310.05208","title":"ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination","created":"2023-10-08","cited_by_count":24,"area":null},{"id":"2203.14009","title":"Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey","created":"2022-03-26","cited_by_count":23,"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":"2106.00669","title":"Discovering Diverse Nearly Optimal Policies with Successor Features","created":"2021-06-01","cited_by_count":20,"area":null},{"id":"2207.09405","title":"Bayesian Generational Population-Based Training","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2302.07515","title":"TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play","created":"2023-02-15","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":"2509.04784","title":"Post-training Large Language Models for Diverse High-Quality Responses","created":"2025-09-05","cited_by_count":19,"area":null},{"id":"2110.15572","title":"Understanding the Effect of Stochasticity in Policy Optimization","created":"2021-10-29","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":"2207.14138","title":"Generating Teammates for Training Robust Ad Hoc Teamwork Agents via Best-Response Diversity","created":"2022-07-28","cited_by_count":17,"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":"2106.04958","title":"Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games","created":"2021-06-09","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":"2305.02128","title":"System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning","created":"2023-05-03","cited_by_count":14,"area":null},{"id":"2305.05239","title":"Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection","created":"2023-05-09","cited_by_count":14,"area":null},{"id":"2102.03140","title":"Sparse Reward Exploration via Novelty Search and Emitters","created":"2021-02-05","cited_by_count":13,"area":null},{"id":"2107.07506","title":"Adaptable Agent Populations via a Generative Model of Policies","created":"2021-07-15","cited_by_count":12,"area":null},{"id":"2208.04957","title":"Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution","created":"2022-08-09","cited_by_count":12,"area":null},{"id":"2207.05631","title":"DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization","created":"2022-07-12","cited_by_count":10,"area":null},{"id":"2203.00715","title":"Learning Robust Real-Time Cultural Transmission without Human Data","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2211.07725","title":"Hierarchically Structured Task-Agnostic Continual Learning","created":"2022-11-14","cited_by_count":9,"area":null},{"id":"2301.08025","title":"Generalization through Diversity: Improving Unsupervised Environment Design","created":"2023-01-19","cited_by_count":9,"area":null},{"id":"2106.15883","title":"Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL","created":"2021-06-30","cited_by_count":8,"area":null},{"id":"2110.12667","title":"Mixture-of-Variational-Experts for Continual Learning","created":"2021-10-25","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":"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":"2106.06232","title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","created":"2021-06-11","cited_by_count":7,"area":null},{"id":"2108.07887","title":"Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay","created":"2021-08-17","cited_by_count":7,"area":null},{"id":"2203.08015","title":"On-the-fly Strategy Adaptation for ad-hoc Agent Coordination","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2206.08888","title":"Fast Population-Based Reinforcement Learning on a Single Machine","created":"2022-06-17","cited_by_count":7,"area":null},{"id":"2207.11584","title":"Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning","created":"2022-07-23","cited_by_count":7,"area":null},{"id":"2212.00211","title":"A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process","created":"2022-12-01","cited_by_count":7,"area":null},{"id":"2111.04873","title":"An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2207.12805","title":"Neural Design for Genetic Perturbation Experiments","created":"2022-07-26","cited_by_count":6,"area":null},{"id":"2305.05116","title":"Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation","created":"2023-05-09","cited_by_count":6,"area":null},{"id":"2305.11476","title":"Learning Diverse Risk Preferences in Population-based Self-play","created":"2023-05-19","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":"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":"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":"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":"2305.01507","title":"A Parameter-free Adaptive Resonance Theory-based Topological Clustering Algorithm Capable of Continual Learning","created":"2023-05-01","cited_by_count":4,"area":null},{"id":"2305.05898","title":"Mixture of personality improved Spiking actor network for efficient multi-agent cooperation","created":"2023-05-10","cited_by_count":4,"area":null},{"id":"2402.02186","title":"Evolution Guided Generative Flow Networks","created":"2024-02-03","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":"2511.12754","title":"Adaptively Coordinating with Novel Partners via Learned Latent Strategies","created":"2025-11-16","cited_by_count":4,"area":null},{"id":"2105.07960","title":"Behavior-based Neuroevolutionary Training in Reinforcement Learning","created":"2021-05-17","cited_by_count":3,"area":null},{"id":"2206.09046","title":"Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis","created":"2022-06-17","cited_by_count":3,"area":null},{"id":"2304.07425","title":"Efficient Quality-Diversity Optimization through Diverse Quality Species","created":"2023-04-14","cited_by_count":3,"area":null},{"id":"2310.14509","title":"Iteratively Learn Diverse Strategies with State Distance Information","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2312.07178","title":"Beyond Expected Return: Accounting for Policy Reproducibility when Evaluating Reinforcement Learning Algorithms","created":"2023-12-12","cited_by_count":3,"area":null},{"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":"2110.08122","title":"Effects of Different Optimization Formulations in Evolutionary Reinforcement Learning on Diverse Behavior Generation","created":"2021-10-15","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":"2111.06005","title":"Agent Spaces","created":"2021-11-11","cited_by_count":1,"area":null},{"id":"2204.11897","title":"Reinforcement Teaching","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2209.12029","title":"Open-Ended Diverse Solution Discovery with Regulated Behavior Patterns for Cross-Domain Adaptation","created":"2022-09-24","cited_by_count":1,"area":null},{"id":"2305.00508","title":"Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward","created":"2023-04-30","cited_by_count":1,"area":null},{"id":"2309.03487","title":"Privacy-preserving Continual Federated Clustering via Adaptive Resonance Theory","created":"2023-09-07","cited_by_count":1,"area":null},{"id":"2501.19153","title":"Test-Time Training Scaling Laws for Chemical Exploration in Drug Design","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2111.14310","title":"How Can Creativity Occur in Multi-Agent Systems?","created":"2021-11-29","cited_by_count":0,"area":null},{"id":"2211.12610","title":"Efficient Exploration using Model-Based Quality-Diversity with Gradients","created":"2022-11-22","cited_by_count":0,"area":null},{"id":"2302.02119","title":"Diversity Induced Environment Design via Self-Play","created":"2023-02-04","cited_by_count":0,"area":null},{"id":"2302.14509","title":"Policy Dispersion in Non-Markovian Environment","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2306.03311","title":"Learning Embeddings for Sequential Tasks Using Population of Agents","created":"2023-06-05","cited_by_count":0,"area":null},{"id":"2506.01568","title":"Trajectory First: A Curriculum for Discovering Diverse Policies","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2605.05020","title":"Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.07775","title":"POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2610.17007","title":"Mixture of GFlowNets","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18808","title":"Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}