{"list":"other","total":56,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"1905.05408","title":"QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning","created":"2019-05-14","cited_by_count":379},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353},{"id":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"id":"2402.01145","title":"ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution","created":"2024-02-02","cited_by_count":276},{"id":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187},{"id":"1512.07679","title":"Deep Reinforcement Learning in Large Discrete Action Spaces","created":"2015-12-24","cited_by_count":161},{"id":"1905.05717","title":"CoLight: Learning Network-level Cooperation for Traffic Signal Control","created":"2019-05-11","cited_by_count":138},{"id":"2003.08039","title":"ROMA: Multi-Agent Reinforcement Learning with Emergent Roles","created":"2020-03-18","cited_by_count":137},{"id":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99},{"id":"2102.07475","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","created":"2021-02-15","cited_by_count":87},{"id":"1809.02121","title":"Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning","created":"2018-09-06","cited_by_count":77},{"id":"2304.07297","title":"Language Instructed Reinforcement Learning for Human-AI Coordination","created":"2023-04-13","cited_by_count":63},{"id":"2005.09382","title":"Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text","created":"2020-05-19","cited_by_count":59},{"id":"1812.01628","title":"Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning","created":"2018-12-04","cited_by_count":53},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49},{"id":"2305.16744","title":"Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought","created":"2023-05-26","cited_by_count":39},{"id":"2311.13884","title":"Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach","created":"2023-11-23","cited_by_count":38},{"id":"2311.16733","title":"LLMs for Science: Usage for Code Generation and Data Analysis","created":"2023-11-28","cited_by_count":34},{"id":"1704.08883","title":"Traffic Light Control Using Deep Policy-Gradient and Value-Function Based Reinforcement Learning","created":"2017-04-28","cited_by_count":33},{"id":"2110.05721","title":"Action-Sufficient State Representation Learning for Control with Structural Constraints","created":"2021-10-12","cited_by_count":31},{"id":"1902.04546","title":"ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning","created":"2019-02-12","cited_by_count":17},{"id":"2305.17568","title":"Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities","created":"2023-05-27","cited_by_count":15},{"id":"2109.08603","title":"Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration","created":"2021-09-17","cited_by_count":14},{"id":"1703.03429","title":"What can you do with a rock? Affordance extraction via word embeddings","created":"2017-03-09","cited_by_count":13},{"id":"2304.14656","title":"From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARL","created":"2023-04-28","cited_by_count":11},{"id":"2306.07542","title":"A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management","created":"2023-06-13","cited_by_count":10},{"id":"2002.08567","title":"Multi-Agent Meta-Reinforcement Learning for Self-Powered and Sustainable Edge Computing Systems","created":"2020-02-20","cited_by_count":9},{"id":"2308.10435","title":"GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systems","created":"2023-08-21","cited_by_count":9},{"id":"2312.14532","title":"DuaLight: Enhancing Traffic Signal Control by Leveraging Scenario-Specific and Scenario-Shared Knowledge","created":"2023-12-22","cited_by_count":9},{"id":"2404.17780","title":"Verco: Learning Coordinated Verbal Communication for Multi-agent Reinforcement Learning","created":"2024-04-27","cited_by_count":7},{"id":"2201.00354","title":"Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference","created":"2022-01-02","cited_by_count":6},{"id":"2203.05285","title":"Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework","created":"2022-03-10","cited_by_count":6},{"id":"1808.03602","title":"Temporal starvation in multi-channel CSMA networks: an analytical framework","created":"2018-08-09","cited_by_count":4},{"id":"2306.08044","title":"Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care","created":"2023-06-13","cited_by_count":2}],"next_cursor":null}