{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"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":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"1802.07740","title":"Machine Theory of Mind","created":"2018-02-21","cited_by_count":226},{"id":"2003.02979","title":"\"Other-Play\" for Zero-Shot Coordination","created":"2020-03-06","cited_by_count":198},{"id":"1902.00506","title":"The Hanabi Challenge: A New Frontier for AI Research","created":"2019-02-01","cited_by_count":197},{"id":"2306.15448","title":"Understanding Social Reasoning in Language Models with Language Models","created":"2023-06-21","cited_by_count":172},{"id":"2310.15421","title":"FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions","created":"2023-10-24","cited_by_count":171},{"id":"2012.08630","title":"Open Problems in Cooperative AI","created":"2020-12-15","cited_by_count":168},{"id":"2110.08176","title":"Collaborating with Humans without Human Data","created":"2021-10-15","cited_by_count":142},{"id":"2402.16801","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","created":"2024-02-26","cited_by_count":88},{"id":"2103.04000","title":"Off-Belief Learning","created":"2021-03-06","cited_by_count":75},{"id":"1806.01830","title":"Relational Deep Reinforcement Learning","created":"2018-06-05","cited_by_count":73},{"id":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70},{"id":"1811.01458","title":"Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning","created":"2018-11-04","cited_by_count":68},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63},{"id":"2109.06275","title":"MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks","created":"2021-09-13","cited_by_count":62},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55},{"id":"1912.02288","title":"Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning","created":"2019-12-04","cited_by_count":48},{"id":"2102.11938","title":"Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others","created":"2021-02-23","cited_by_count":39},{"id":"2403.04253","title":"Mastering Memory Tasks with World Models","created":"2024-03-07","cited_by_count":38},{"id":"2106.06613","title":"A New Formalism, Method and Open Issues for Zero-Shot Coordination","created":"2021-06-11","cited_by_count":33},{"id":"2207.07166","title":"K-level Reasoning for Zero-Shot Coordination in Hanabi","created":"2022-07-14","cited_by_count":32},{"id":"2402.18496","title":"Language Models Represent Beliefs of Self and Others","created":"2024-02-28","cited_by_count":31},{"id":"2201.12436","title":"Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination","created":"2022-01-28","cited_by_count":23},{"id":"2203.16540","title":"Mind the gap: Challenges of deep learning approaches to Theory of Mind","created":"2022-03-30","cited_by_count":21},{"id":"2307.01158","title":"Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learning","created":"2023-07-03","cited_by_count":19},{"id":"2104.02841","title":"Learning Triadic Belief Dynamics in Nonverbal Communication from Videos","created":"2021-04-07","cited_by_count":17},{"id":"2210.12124","title":"Equivariant Networks for Zero-Shot Coordination","created":"2022-10-21","cited_by_count":16},{"id":"2503.17821","title":"OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination","created":"2025-03-22","cited_by_count":16},{"id":"2208.04957","title":"Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution","created":"2022-08-09","cited_by_count":12},{"id":"2101.09328","title":"Theory of Mind for Deep Reinforcement Learning in Hanabi","created":"2021-01-22","cited_by_count":11},{"id":"2406.17949","title":"The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design","created":"2024-06-25","cited_by_count":11},{"id":"2506.14990","title":"MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning","created":"2025-06-17","cited_by_count":11},{"id":"2405.12621","title":"Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisition","created":"2024-05-21","cited_by_count":10},{"id":"2305.11271","title":"Towards Collaborative Plan Acquisition through Theory of Mind Modeling in Situated Dialogue","created":"2023-05-18","cited_by_count":9},{"id":"2206.10665","title":"BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios","created":"2022-06-21","cited_by_count":8},{"id":"2312.07122","title":"Neural Reasoning About Agents' Goals, Preferences, and Actions","created":"2023-12-12","cited_by_count":8},{"id":"2506.21490","title":"Ad-Hoc Human-AI Coordination Challenge","created":"2025-06-26","cited_by_count":8},{"id":"2407.06762","title":"Explicit Modelling of Theory of Mind for Belief Prediction in Nonverbal Social Interactions","created":"2024-07-09","cited_by_count":6},{"id":"2502.01711","title":"Expected Return Symmetries","created":"2025-02-03","cited_by_count":5},{"id":"2503.14555","title":"A Generalist Hanabi Agent","created":"2025-03-17","cited_by_count":5},{"id":"2310.16590","title":"$\\mathbb{VD}$-$\\mathbb{GR}$: Boosting $\\mathbb{V}$isual $\\mathbb{D}$ialog with Cascaded Spatial-Temporal Multi-Modal $\\mathbb{GR}$aphs","created":"2023-10-25","cited_by_count":4},{"id":"2508.06336","title":"Unsupervised Partner Design Enables Robust Ad-hoc Teamwork","created":"2025-08-08","cited_by_count":3},{"id":"1805.06020","title":"Do deep reinforcement learning agents model intentions?","created":"2018-05-15","cited_by_count":2}],"next_cursor":null}