{"total":38,"rows":[{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148,"area":null},{"id":"2106.03894","title":"Differentiable Quality Diversity","created":"2021-06-07","cited_by_count":72,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2304.02868","title":"Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions","created":"2023-04-06","cited_by_count":30,"area":null},{"id":"2407.14931","title":"POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding","created":"2024-07-20","cited_by_count":21,"area":null},{"id":"2203.10603","title":"Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects","created":"2022-03-20","cited_by_count":17,"area":null},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2204.09787","title":"Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency","created":"2022-04-20","cited_by_count":16,"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":"2202.09028","title":"On the Implicit Bias Towards Minimal Depth of Deep Neural Networks","created":"2022-02-18","cited_by_count":12,"area":null},{"id":"2507.22028","title":"From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning","created":"2025-07-29","cited_by_count":12,"area":null},{"id":"2306.01460","title":"ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2305.06807","title":"Information Design in Multi-Agent Reinforcement Learning","created":"2023-05-08","cited_by_count":9,"area":null},{"id":"2405.11778","title":"Efficient Multi-agent Reinforcement Learning by Planning","created":"2024-05-20","cited_by_count":9,"area":null},{"id":"2112.14570","title":"Lyapunov Exponents for Diversity in Differentiable Games","created":"2021-12-24","cited_by_count":8,"area":null},{"id":"2201.11994","title":"FCMNet: Full Communication Memory Net for Team-Level Cooperation in Multi-Agent Systems","created":"2022-01-28","cited_by_count":7,"area":null},{"id":"2301.12033","title":"Norm-based Generalization Bounds for Compositionally Sparse Neural Networks","created":"2023-01-28","cited_by_count":7,"area":null},{"id":"2601.03335","title":"Digital Red Queen: Adversarial Program Evolution in Core War with LLMs","created":"2026-01-06","cited_by_count":7,"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":"2203.10941","title":"Transfer Dynamics in Emergent Evolutionary Curricula","created":"2022-03-03","cited_by_count":6,"area":null},{"id":"2212.02064","title":"E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2303.01668","title":"RePreM: Representation Pre-training with Masked Model for Reinforcement Learning","created":"2023-03-03","cited_by_count":5,"area":null},{"id":"2301.04605","title":"Exploring the Approximation Capabilities of Multiplicative Neural Networks for Smooth Functions","created":"2023-01-11","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":"2306.13028","title":"Transferable Curricula through Difficulty Conditioned Generators","created":"2023-06-22","cited_by_count":4,"area":null},{"id":"2108.11010","title":"Adversary agent reinforcement learning for pursuit-evasion","created":"2021-08-25","cited_by_count":1,"area":null},{"id":"2205.05248","title":"Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learning","created":"2022-05-11","cited_by_count":1,"area":null},{"id":"2308.12445","title":"An Intentional Forgetting-Driven Self-Healing Method For Deep Reinforcement Learning Systems","created":"2023-08-23","cited_by_count":1,"area":null},{"id":"2409.18695","title":"KALE-LM-Chem: Vision and Practice Toward an AI Brain for Chemistry","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2505.03818","title":"Program Semantic Inequivalence Game with Large Language Models","created":"2025-05-02","cited_by_count":1,"area":null},{"id":"2104.05710","title":"Systemic formalisation of Cyber-Physical-Social System (CPSS): A systematic literature review","created":"2021-04-11","cited_by_count":0,"area":null},{"id":"2104.10845","title":"Optimize Neural Fictitious Self-Play in Regret Minimization Thinking","created":"2021-04-22","cited_by_count":0,"area":null},{"id":"2201.05089","title":"Using Computational Intelligence for solving the Ornstein-Zernike equation","created":"2021-11-17","cited_by_count":0,"area":null},{"id":"2211.14395","title":"Deep Learning Training Procedure Augmentations","created":"2022-11-25","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":"2403.07932","title":"Feint Behaviors and Strategies: Formalization, Implementation and Evaluation","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2403.10824","title":"LookALike: Human Mimicry based collaborative decision making","created":"2024-03-16","cited_by_count":0,"area":null},{"id":"2602.08517","title":"TreeTensor: Boost AI System on Nested Data with Constrained Tree-Like Tensor","created":"2026-02-09","cited_by_count":0,"area":null}],"next_cursor":null}