{"total":220,"rows":[{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942,"area":null},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228,"area":null},{"id":"2203.08975","title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","created":"2022-03-16","cited_by_count":104,"area":null},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87,"area":null},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82,"area":null},{"id":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69,"area":null},{"id":"2207.11201","title":"Target-Driven Structured Transformer Planner for Vision-Language Navigation","created":"2022-07-19","cited_by_count":58,"area":null},{"id":"2102.04402","title":"Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning","created":"2021-02-08","cited_by_count":56,"area":null},{"id":"2102.12321","title":"AGENT: A Benchmark for Core Psychological Reasoning","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2110.15349","title":"Learning to Ground Multi-Agent Communication with Autoencoders","created":"2021-10-28","cited_by_count":37,"area":null},{"id":"2204.09280","title":"Reinforced Structured State-Evolution for Vision-Language Navigation","created":"2022-04-20","cited_by_count":37,"area":null},{"id":"2104.05565","title":"Survey on reinforcement learning for language processing","created":"2021-04-12","cited_by_count":31,"area":null},{"id":"2104.02871","title":"On the Critical Role of Conventions in Adaptive Human-AI Collaboration","created":"2021-04-07","cited_by_count":27,"area":null},{"id":"2104.05857","title":"From partners to populations: A hierarchical Bayesian account of coordination and convention","created":"2021-04-12","cited_by_count":27,"area":null},{"id":"2106.02067","title":"Learning to Draw: Emergent Communication through Sketching","created":"2021-06-03","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":"2108.01843","title":"Model-Based Opponent Modeling","created":"2021-08-04","cited_by_count":22,"area":null},{"id":"2105.00931","title":"GridToPix: Training Embodied Agents with Minimal Supervision","created":"2021-04-14","cited_by_count":21,"area":null},{"id":"2412.05255","title":"TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft","created":"2024-12-06","cited_by_count":21,"area":null},{"id":"2107.08170","title":"Megaverse: Simulating Embodied Agents at One Million Experiences per Second","created":"2021-07-17","cited_by_count":20,"area":null},{"id":"2108.01828","title":"Emergent Discrete Communication in Semantic Spaces","created":"2021-08-04","cited_by_count":20,"area":null},{"id":"2405.15815","title":"A social path to human-like artificial intelligence","created":"2024-05-22","cited_by_count":20,"area":null},{"id":"2103.01171","title":"Expected Value of Communication for Planning in Ad Hoc Teamwork","created":"2021-03-01","cited_by_count":19,"area":null},{"id":"2110.05769","title":"Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2203.13344","title":"Linking Emergent and Natural Languages via Corpus Transfer","created":"2022-03-24","cited_by_count":19,"area":null},{"id":"2101.10276","title":"Emergent Communication under Competition","created":"2021-01-25","cited_by_count":18,"area":null},{"id":"2107.01151","title":"Collaborative Visual Navigation","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2108.03319","title":"Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning","created":"2021-08-06","cited_by_count":18,"area":null},{"id":"2110.07594","title":"The Neural MMO Platform for Massively Multiagent Research","created":"2021-10-14","cited_by_count":17,"area":null},{"id":"2111.14210","title":"Emergent Graphical Conventions in a Visual Communication Game","created":"2021-11-28","cited_by_count":16,"area":null},{"id":"2203.07676","title":"An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobility","created":"2022-03-15","cited_by_count":16,"area":null},{"id":"2204.03516","title":"Distributed Reinforcement Learning for Robot Teams: A Review","created":"2022-04-07","cited_by_count":16,"area":null},{"id":"2206.02640","title":"Policy Optimization for Markov Games: Unified Framework and Faster Convergence","created":"2022-06-06","cited_by_count":16,"area":null},{"id":"2102.11344","title":"HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving","created":"2021-02-22","cited_by_count":15,"area":null},{"id":"2105.08268","title":"Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach","created":"2021-05-18","cited_by_count":14,"area":null},{"id":"2302.13851","title":"Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks","created":"2023-02-27","cited_by_count":14,"area":null},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2102.00824","title":"HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging","created":"2021-01-18","cited_by_count":13,"area":null},{"id":"2109.06232","title":"The Emergence of the Shape Bias Results from Communicative Efficiency","created":"2021-09-13","cited_by_count":13,"area":null},{"id":"2112.09012","title":"Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2203.08257","title":"Differentiable Multi-Agent Actor-Critic for Multi-Step Radiology Report Summarization","created":"2022-03-15","cited_by_count":13,"area":null},{"id":"2308.02541","title":"Towards More Human-like AI Communication: A Review of Emergent Communication Research","created":"2023-08-01","cited_by_count":13,"area":null},{"id":"2406.02081","title":"FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2111.06464","title":"Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication","created":"2021-11-11","cited_by_count":12,"area":null},{"id":"2201.01247","title":"Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradients","created":"2022-01-04","cited_by_count":12,"area":null},{"id":"2209.09845","title":"Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL","created":"2022-09-20","cited_by_count":12,"area":null},{"id":"2301.13083","title":"Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off","created":"2023-01-30","cited_by_count":12,"area":null},{"id":"2103.12710","title":"Spatial Intention Maps for Multi-Agent Mobile Manipulation","created":"2021-03-23","cited_by_count":11,"area":null},{"id":"2210.04365","title":"ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward","created":"2022-10-09","cited_by_count":11,"area":null},{"id":"2311.04453","title":"Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2506.14990","title":"MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning","created":"2025-06-17","cited_by_count":11,"area":null},{"id":"2110.14241","title":"Dynamic population-based meta-learning for multi-agent communication with natural language","created":"2021-10-27","cited_by_count":10,"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":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2305.10154","title":"Cultural evolution via iterated learning and communication explains efficient color naming systems","created":"2023-05-17","cited_by_count":10,"area":null},{"id":"2306.07542","title":"A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2308.10284","title":"Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi","created":"2023-08-20","cited_by_count":10,"area":null},{"id":"2408.14597","title":"On Centralized Critics in Multi-Agent Reinforcement Learning","created":"2024-08-26","cited_by_count":10,"area":null},{"id":"2307.16186","title":"ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning","created":"2023-07-30","cited_by_count":9,"area":null},{"id":"2310.08089","title":"Learning Regularized Monotone Graphon Mean-Field Games","created":"2023-10-12","cited_by_count":9,"area":null},{"id":"2106.05727","title":"Cooperative Multi-Agent Fairness and Equivariant Policies","created":"2021-06-10","cited_by_count":8,"area":null},{"id":"2107.09598","title":"Learning Altruistic Behaviours in Reinforcement Learning without External Rewards","created":"2021-07-20","cited_by_count":8,"area":null},{"id":"2110.00121","title":"Emergence of Theory of Mind Collaboration in Multiagent Systems","created":"2021-09-30","cited_by_count":8,"area":null},{"id":"2207.00088","title":"Towards Human-Agent Communication via the Information Bottleneck Principle","created":"2022-06-30","cited_by_count":8,"area":null},{"id":"2308.03358","title":"RGMComm: Return Gap Minimization via Discrete Communications in Multi-Agent Reinforcement Learning","created":"2023-08-07","cited_by_count":8,"area":null},{"id":"2603.00730","title":"MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning","created":"2026-02-28","cited_by_count":8,"area":null},{"id":"2107.00956","title":"SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents","created":"2021-07-02","cited_by_count":7,"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":"2203.08015","title":"On-the-fly Strategy Adaptation for ad-hoc Agent Coordination","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2310.09506","title":"Towards Semantic Communication Protocols for 6G: From Protocol Learning to Language-Oriented Approaches","created":"2023-10-14","cited_by_count":7,"area":null},{"id":"2105.05145","title":"Visual Perspective Taking for Opponent Behavior Modeling","created":"2021-05-11","cited_by_count":6,"area":null},{"id":"2106.11156","title":"Multi-Agent Curricula and Emergent Implicit Signaling","created":"2021-06-21","cited_by_count":6,"area":null},{"id":"2201.07452","title":"Interpretable Learned Emergent Communication for Human-Agent Teams","created":"2022-01-19","cited_by_count":6,"area":null},{"id":"2204.04687","title":"MA-Dreamer: Coordination and communication through shared imagination","created":"2022-04-10","cited_by_count":6,"area":null},{"id":"2204.05669","title":"An Analysis of Discretization Methods for Communication Learning with Multi-Agent Reinforcement Learning","created":"2022-04-12","cited_by_count":6,"area":null},{"id":"2205.12880","title":"Trust-based Consensus in Multi-Agent Reinforcement Learning Systems","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2208.04554","title":"Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generation","created":"2022-08-09","cited_by_count":6,"area":null},{"id":"2305.05566","title":"SMAClite: A Lightweight Environment for Multi-Agent Reinforcement Learning","created":"2023-05-09","cited_by_count":6,"area":null},{"id":"2310.17485","title":"Fair collaborative vehicle routing: A deep multi-agent reinforcement learning approach","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2101.10253","title":"The emergence of visual semantics through communication games","created":"2021-01-25","cited_by_count":5,"area":null},{"id":"2108.03952","title":"Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces","created":"2021-08-09","cited_by_count":5,"area":null},{"id":"2111.01100","title":"Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environments","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2207.02249","title":"Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning","created":"2022-07-05","cited_by_count":5,"area":null},{"id":"2302.03439","title":"Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning","created":"2023-02-07","cited_by_count":5,"area":null},{"id":"2302.12515","title":"AC2C: Adaptively Controlled Two-Hop Communication for Multi-Agent Reinforcement Learning","created":"2023-02-24","cited_by_count":5,"area":null},{"id":"2304.11632","title":"Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective","created":"2023-04-23","cited_by_count":5,"area":null},{"id":"2304.14511","title":"Visual Referential Games Further the Emergence of Disentangled Representations","created":"2023-04-27","cited_by_count":5,"area":null},{"id":"2403.08936","title":"Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning","created":"2024-03-13","cited_by_count":5,"area":null},{"id":"2405.12109","title":"Linguistic Structure from a Bottleneck on Sequential Information Processing","created":"2024-05-20","cited_by_count":5,"area":null},{"id":"2408.05686","title":"The Bandit Whisperer: Communication Learning for Restless Bandits","created":"2024-08-11","cited_by_count":5,"area":null},{"id":"2408.15381","title":"On Stateful Value Factorization in Multi-Agent Reinforcement Learning","created":"2024-08-27","cited_by_count":5,"area":null},{"id":"2502.04773","title":"An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks","created":"2025-02-07","cited_by_count":5,"area":null},{"id":"2104.09557","title":"Learning to Communicate with Strangers via Channel Randomisation Methods","created":"2021-04-19","cited_by_count":4,"area":null},{"id":"2111.15611","title":"The Power of Communication in a Distributed Multi-Agent System","created":"2021-11-30","cited_by_count":4,"area":null},{"id":"2201.02734","title":"Building Human-like Communicative Intelligence: A Grounded Perspective","created":"2022-01-02","cited_by_count":4,"area":null},{"id":"2207.07025","title":"Learning to translate by learning to communicate","created":"2022-07-14","cited_by_count":4,"area":null},{"id":"2208.05083","title":"Reducing Exploitability with Population Based Training","created":"2022-08-10","cited_by_count":4,"area":null},{"id":"2211.01480","title":"Over-communicate no more: Situated RL agents learn concise communication protocols","created":"2022-11-02","cited_by_count":4,"area":null},{"id":"2302.08084","title":"Learning Multi-Object Positional Relationships via Emergent Communication","created":"2023-02-16","cited_by_count":4,"area":null}],"next_cursor":"100"}