{"total":150,"rows":[{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2111.00053","title":"Symbolic Regression via Neural-Guided Genetic Programming Population Seeding","created":"2021-10-29","cited_by_count":101,"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":"2111.11188","title":"Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification","created":"2021-11-22","cited_by_count":61,"area":"offlinerl"},{"id":"2109.00540","title":"Variational Quantum Reinforcement Learning via Evolutionary Optimization","created":"2021-09-01","cited_by_count":50,"area":null},{"id":"2403.01131","title":"LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation","created":"2024-03-02","cited_by_count":45,"area":null},{"id":"2205.01447","title":"Model-Free Opponent Shaping","created":"2022-05-03","cited_by_count":44,"area":null},{"id":"2211.11260","title":"Discovering Evolution Strategies via Meta-Black-Box Optimization","created":"2022-11-21","cited_by_count":44,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2212.04180","title":"evosax: JAX-based Evolution Strategies","created":"2022-12-08","cited_by_count":41,"area":null},{"id":"2509.24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","created":"2025-09-29","cited_by_count":34,"area":null},{"id":"2303.04150","title":"Evolutionary Reinforcement Learning: A Survey","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2401.00282","title":"Deep Generative Symbolic Regression","created":"2023-12-30","cited_by_count":28,"area":null},{"id":"2503.13415","title":"A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives","created":"2025-03-17","cited_by_count":27,"area":"agents"},{"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":"2511.16652","title":"Evolution Strategies at the Hyperscale","created":"2025-11-20","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":"2304.03094","title":"PopulAtion Parameter Averaging (PAPA)","created":"2023-04-06","cited_by_count":23,"area":null},{"id":"2306.03693","title":"ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networks","created":"2023-06-06","cited_by_count":23,"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":"2204.11674","title":"HyperNCA: Growing Developmental Networks with Neural Cellular Automata","created":"2022-04-25","cited_by_count":18,"area":null},{"id":"2207.13676","title":"Open Source Vizier: Distributed Infrastructure and API for Reliable and Flexible Blackbox Optimization","created":"2022-07-27","cited_by_count":18,"area":null},{"id":"2306.03257","title":"Generating Private Synthetic Data with Genetic Algorithms","created":"2023-06-05","cited_by_count":18,"area":null},{"id":"2102.05710","title":"Derivative-Free Reinforcement Learning: A Review","created":"2021-02-10","cited_by_count":15,"area":null},{"id":"2104.13997","title":"MAGMA: An Optimization Framework for Mapping Multiple DNNs on Multiple Accelerator Cores","created":"2021-04-28","cited_by_count":15,"area":null},{"id":"2205.00293","title":"TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning","created":"2022-04-30","cited_by_count":15,"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":"2407.07082","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","created":"2024-07-09","cited_by_count":14,"area":"deeprl"},{"id":"2103.03526","title":"Meta Learning Black-Box Population-Based Optimizers","created":"2021-03-05","cited_by_count":13,"area":null},{"id":"2405.03728","title":"Pretrained Optimization Model for Zero-Shot Black Box Optimization","created":"2024-05-06","cited_by_count":13,"area":null},{"id":"2411.12746","title":"A Review of Reinforcement Learning in Financial Applications","created":"2024-11-01","cited_by_count":13,"area":"deeprl"},{"id":"2107.07046","title":"Backprop-Free Reinforcement Learning with Active Neural Generative Coding","created":"2021-07-10","cited_by_count":12,"area":null},{"id":"2104.15064","title":"Black-box adversarial attacks using Evolution Strategies","created":"2021-04-30","cited_by_count":11,"area":null},{"id":"2408.10932","title":"The Evolution of Reinforcement Learning in Quantitative Finance: A Survey","created":"2024-08-20","cited_by_count":11,"area":"deeprl"},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"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":"2107.00140","title":"Applications of the Free Energy Principle to Machine Learning and Neuroscience","created":"2021-06-30","cited_by_count":9,"area":null},{"id":"2406.11905","title":"EvIL: Evolution Strategies for Generalisable Imitation Learning","created":"2024-06-15","cited_by_count":8,"area":"offlinerl"},{"id":"2503.24322","title":"NoProp: Training Neural Networks without Full Back-propagation or Full Forward-propagation","created":"2025-03-31","cited_by_count":8,"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":"2201.11220","title":"DiGamma: Domain-aware Genetic Algorithm for HW-Mapping Co-optimization for DNN Accelerators","created":"2022-01-26","cited_by_count":7,"area":null},{"id":"2409.05846","title":"An Introduction to Quantum Reinforcement Learning (QRL)","created":"2024-09-09","cited_by_count":7,"area":"deeprl"},{"id":"2509.22963","title":"Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces","created":"2025-09-26","cited_by_count":7,"area":"diffusion"},{"id":"2601.20861","title":"Evolutionary Strategies lead to Catastrophic Forgetting in LLMs","created":"2026-01-28","cited_by_count":7,"area":null},{"id":"2106.07611","title":"Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantization","created":"2021-06-14","cited_by_count":6,"area":null},{"id":"2204.04817","title":"Effective Mutation Rate Adaptation through Group Elite Selection","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2112.07057","title":"NEORL: NeuroEvolution Optimization with Reinforcement Learning","created":"2021-12-01","cited_by_count":5,"area":null},{"id":"2302.03281","title":"Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning","created":"2023-02-07","cited_by_count":5,"area":null},{"id":"2311.05546","title":"Multi-Agent Quantum Reinforcement Learning using Evolutionary Optimization","created":"2023-11-09","cited_by_count":5,"area":null},{"id":"2406.15042","title":"Behaviour Distillation","created":"2024-06-21","cited_by_count":5,"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":"2406.00294","title":"Creative Text-to-Audio Generation via Synthesizer Programming","created":"2024-06-01","cited_by_count":4,"area":null},{"id":"2504.17578","title":"Advancing CMA-ES with Learning-Based Cooperative Coevolution for Scalable Optimization","created":"2025-04-24","cited_by_count":4,"area":"deeprl"},{"id":"2101.04383","title":"Interpretable discovery of new semiconductors with machine learning","created":"2021-01-12","cited_by_count":3,"area":null},{"id":"2104.05610","title":"A coevolutionary approach to deep multi-agent reinforcement learning","created":"2021-04-12","cited_by_count":3,"area":null},{"id":"2203.10844","title":"Multitask Neuroevolution for Reinforcement Learning with Long and Short Episodes","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2208.12136","title":"A Comparison of Reinforcement Learning Frameworks for Software Testing Tasks","created":"2022-08-25","cited_by_count":3,"area":null},{"id":"2211.02759","title":"Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI","created":"2022-11-04","cited_by_count":3,"area":null},{"id":"2505.10762","title":"Deep Symbolic Optimization: Reinforcement Learning for Symbolic Mathematics","created":"2025-05-16","cited_by_count":3,"area":"deeprl"},{"id":"2108.06911","title":"Optimal Actor-Critic Policy with Optimized Training Datasets","created":"2021-08-16","cited_by_count":2,"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":"2203.12853","title":"Direct evaluation of progression or regression of disease burden in brain metastatic disease with Deep Neuroevolution","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2207.02134","title":"Balancing Profit, Risk, and Sustainability for Portfolio Management","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2211.00828","title":"Synthesizing Programs with Continuous Optimization","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2303.01584","title":"Evolutionary Augmentation Policy Optimization for Self-supervised Learning","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2306.00045","title":"Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2308.12053","title":"Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2312.12606","title":"Optimizing Neural Networks with Gradient Lexicase Selection","created":"2023-12-19","cited_by_count":2,"area":null},{"id":"2402.06912","title":"Solving Deep Reinforcement Learning Tasks with Evolution Strategies and Linear Policy Networks","created":"2024-02-10","cited_by_count":2,"area":"deeprl"},{"id":"2402.07928","title":"Abstracted Trajectory Visualization for Explainability in Reinforcement Learning","created":"2024-02-05","cited_by_count":2,"area":"deeprl"},{"id":"2403.04937","title":"Gradient-free neural topology optimization: Towards effective fracture-resistant designs","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2408.01187","title":"Optimizing Variational Quantum Circuits Using Metaheuristic Strategies in Reinforcement Learning","created":"2024-08-02","cited_by_count":2,"area":"deeprl"},{"id":"2501.13883","title":"Utilizing Evolution Strategies to Train Transformers in Reinforcement Learning","created":"2025-01-23","cited_by_count":2,"area":"deeprl"},{"id":"2505.22696","title":"When Does Neuroevolution Outcompete Reinforcement Learning in Transfer Learning Tasks?","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2506.00299","title":"Inference-Time Alignment of Diffusion Models via Evolutionary Algorithms","created":"2025-05-30","cited_by_count":2,"area":"diffusion"},{"id":"2512.16200","title":"Explicit and Non-asymptotic Query Complexities of Rank-Based Zeroth-order Algorithms on Smooth Functions","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2512.16406","title":"Hypernetworks That Evolve Themselves","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2606.26327","title":"EVOM: Agentic Meta-Evolution of Actor-Critic Architectures for Reinforcement Learning","created":"2026-06-24","cited_by_count":2,"area":"agents"},{"id":"2607.09399","title":"Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2001.01683","title":"Deep Innovation Protection: Confronting the Credit Assignment Problem in Training Heterogeneous Neural Architectures","created":"2019-12-29","cited_by_count":1,"area":"wm"},{"id":"2103.06846","title":"Policy Search with Rare Significant Events: Choosing the Right Partner to Cooperate with","created":"2021-03-11","cited_by_count":1,"area":null},{"id":"2103.10790","title":"Quality Evolvability ES: Evolving Individuals With a Distribution of Well Performing and Diverse Offspring","created":"2021-03-19","cited_by_count":1,"area":null},{"id":"2104.04768","title":"Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms","created":"2021-04-10","cited_by_count":1,"area":null},{"id":"2112.03670","title":"Hybrid Self-Attention NEAT: A novel evolutionary approach to improve the NEAT algorithm","created":"2021-12-07","cited_by_count":1,"area":null},{"id":"2201.04502","title":"Dyna-T: Dyna-Q and Upper Confidence Bounds Applied to Trees","created":"2022-01-12","cited_by_count":1,"area":null},{"id":"2201.04815","title":"Direct Mutation and Crossover in Genetic Algorithms Applied to Reinforcement Learning Tasks","created":"2022-01-13","cited_by_count":1,"area":null},{"id":"2201.12518","title":"Zeroth-Order Actor-Critic: An Evolutionary Framework for Sequential Decision Problems","created":"2022-01-29","cited_by_count":1,"area":null},{"id":"2304.12932","title":"Evolving Three Dimension (3D) Abstract Art: Fitting Concepts by Language","created":"2023-04-24","cited_by_count":1,"area":null},{"id":"2306.09991","title":"Evolutionary Algorithms in the Light of SGD: Limit Equivalence, Minima Flatness, and Transfer Learning","created":"2023-05-20","cited_by_count":1,"area":null},{"id":"2402.05187","title":"Learning mirror maps in policy mirror descent","created":"2024-02-07","cited_by_count":1,"area":"deeprl"},{"id":"2408.09493","title":"Ancestral Reinforcement Learning: Unifying Zeroth-Order Optimization and Genetic Algorithms for Reinforcement Learning","created":"2024-08-18","cited_by_count":1,"area":"deeprl"},{"id":"2501.02200","title":"Learning Evolution via Optimization Knowledge Adaptation","created":"2025-01-04","cited_by_count":1,"area":null},{"id":"2505.19423","title":"Surrogate-Assisted Evolutionary Reinforcement Learning Based on Autoencoder and Hyperbolic Neural Network","created":"2025-05-26","cited_by_count":1,"area":"deeprl"},{"id":"2507.03793","title":"Learning Dark Souls Combat Through Pixel Input With Neuroevolution","created":"2025-07-04","cited_by_count":1,"area":null},{"id":"2508.08526","title":"Playing Atari Space Invaders with Sparse Cosine Optimized Policy Evolution","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2509.14894","title":"Leveraging Reinforcement Learning, Genetic Algorithms and Transformers for background determination in particle physics","created":"2025-09-18","cited_by_count":1,"area":"deeprl"},{"id":"2510.18221","title":"The Emergence of Complex Behavior in Large-Scale Ecological Environments","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2512.13399","title":"Dual-Evolving Reinforcement Learning for Automated Reward Design","created":"2025-12-15","cited_by_count":1,"area":"deeprl"}],"next_cursor":"100"}