{"list":"other","total":59,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1706.05296","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","created":"2017-06-16","cited_by_count":503},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"2302.01560","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","created":"2023-02-03","cited_by_count":398},{"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":"1810.02912","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","created":"2018-10-05","cited_by_count":261},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186},{"id":"2310.07899","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","created":"2023-10-11","cited_by_count":134},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128},{"id":"1707.09183","title":"A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity","created":"2017-07-28","cited_by_count":94},{"id":"2309.16739","title":"Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities","created":"2023-09-28","cited_by_count":90},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83},{"id":"2308.13724","title":"ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning","created":"2023-08-26","cited_by_count":77},{"id":"2306.12194","title":"Split Learning in 6G Edge Networks","created":"2023-06-21","cited_by_count":68},{"id":"2403.13101","title":"AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks","created":"2024-03-19","cited_by_count":64},{"id":"2407.00952","title":"SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models","created":"2024-07-01","cited_by_count":62},{"id":"2404.06448","title":"Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2024-04-09","cited_by_count":49},{"id":"1910.01465","title":"Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics","created":"2019-10-03","cited_by_count":47},{"id":"2311.01483","title":"FedSN: A Federated Learning Framework over Heterogeneous LEO Satellite Networks","created":"2023-11-02","cited_by_count":38},{"id":"2412.07197","title":"Hierarchical Split Federated Learning: Convergence Analysis and System Optimization","created":"2024-12-10","cited_by_count":38},{"id":"2309.06687","title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics","created":"2023-09-13","cited_by_count":36},{"id":"2110.02793","title":"Multi-Agent Constrained Policy Optimisation","created":"2021-10-06","cited_by_count":35},{"id":"2505.02795","title":"HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models","created":"2025-05-05","cited_by_count":31},{"id":"2404.11943","title":"AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration","created":"2024-04-18","cited_by_count":26},{"id":"2501.01293","title":"LEO-Split: A Semi-Supervised Split Learning Framework over LEO Satellite Networks","created":"2025-01-02","cited_by_count":22},{"id":"2006.11917","title":"Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement Learning","created":"2020-06-21","cited_by_count":21},{"id":"2310.08922","title":"LLaMA Rider: Spurring Large Language Models to Explore the Open World","created":"2023-10-13","cited_by_count":21},{"id":"2410.02592","title":"IC3M: In-Car Multimodal Multi-object Monitoring for Abnormal Status of Both Driver and Passengers","created":"2024-10-03","cited_by_count":20},{"id":"2209.10113","title":"Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning","created":"2022-09-20","cited_by_count":18},{"id":"2410.00392","title":"MERIT: Multimodal Wearable Vital Sign Waveform Monitoring","created":"2024-10-01","cited_by_count":16},{"id":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","cited_by_count":15},{"id":"2506.08426","title":"HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systems","created":"2025-06-10","cited_by_count":15},{"id":"2405.15542","title":"SATSense: Multi-Satellite Collaborative Framework for Spectrum Sensing","created":"2024-05-24","cited_by_count":14},{"id":"1909.08747","title":"Edge-Computing-Enabled Smart Cities: A Comprehensive Survey","created":"2019-09-11","cited_by_count":13},{"id":"2501.02775","title":"Constructing 4D Radio Map in LEO Satellite Networks with Limited Samples","created":"2025-01-06","cited_by_count":13},{"id":"2405.15705","title":"Sums: Sniffing Unknown Multiband Signals under Low Sampling Rates","created":"2024-05-24","cited_by_count":12},{"id":"2501.03562","title":"Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective","created":"2025-01-07","cited_by_count":10},{"id":"2508.09085","title":"Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring","created":"2025-08-12","cited_by_count":10},{"id":"2308.02345","title":"Communication-Efficient Decentralized Multi-Agent Reinforcement Learning for Cooperative Adaptive Cruise Control","created":"2023-08-04","cited_by_count":9},{"id":"2310.00481","title":"LANCAR: Leveraging Language for Context-Aware Robot Locomotion in Unstructured Environments","created":"2023-09-30","cited_by_count":9},{"id":"1909.06900","title":"Exploiting Fast Decaying and Locality in Multi-Agent MDP with Tree Dependence Structure","created":"2019-09-15","cited_by_count":8},{"id":"2309.16347","title":"Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks","created":"2023-09-28","cited_by_count":8},{"id":"2503.20613","title":"State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning","created":"2025-03-26","cited_by_count":8},{"id":"2503.20844","title":"Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks","created":"2025-03-26","cited_by_count":7},{"id":"2306.05696","title":"Embodied Executable Policy Learning with Language-based Scene Summarization","created":"2023-06-09","cited_by_count":6},{"id":"2403.11607","title":"AGRNav: Efficient and Energy-Saving Autonomous Navigation for Air-Ground Robots in Occlusion-Prone Environments","created":"2024-03-18","cited_by_count":6},{"id":"2403.08936","title":"Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning","created":"2024-03-13","cited_by_count":5},{"id":"2509.17398","title":"Optimizing Split Federated Learning with Unstable Client Participation","created":"2025-09-22","cited_by_count":5},{"id":"2509.15032","title":"Sample Efficient Experience Replay in Non-stationary Environments","created":"2025-09-18","cited_by_count":3},{"id":"2311.03756","title":"Learning Decentralized Traffic Signal Controllers with Multi-Agent Graph Reinforcement Learning","created":"2023-11-07","cited_by_count":2},{"id":"2410.05079","title":"HE-Nav: A High-Performance and Efficient Navigation System for Aerial-Ground Robots in Cluttered Environments","created":"2024-10-07","cited_by_count":1}],"next_cursor":null}