{"list":"other","total":73,"rows":[{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"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":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"id":"1804.10332","title":"Sim-to-Real: Learning Agile Locomotion For Quadruped Robots","created":"2018-04-27","cited_by_count":319},{"id":"1804.06516","title":"Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization","created":"2018-04-18","cited_by_count":294},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1711.00832","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","created":"2017-11-02","cited_by_count":268},{"id":"1703.04908","title":"Emergence of Grounded Compositional Language in Multi-Agent Populations","created":"2017-03-15","cited_by_count":263},{"id":"1907.11180","title":"Google Research Football: A Novel Reinforcement Learning Environment","created":"2019-07-25","cited_by_count":260},{"id":"1704.03003","title":"Automated Curriculum Learning for Neural Networks","created":"2017-04-10","cited_by_count":257},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"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":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","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":"1901.01753","title":"Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions","created":"2019-01-07","cited_by_count":192},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173},{"id":"2110.08176","title":"Collaborating with Humans without Human Data","created":"2021-10-15","cited_by_count":142},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138},{"id":"1810.00123","title":"Generalization and Regularization in DQN","created":"2018-09-29","cited_by_count":118},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111},{"id":"2003.08536","title":"Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions","created":"2020-03-19","cited_by_count":106},{"id":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"id":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63},{"id":"1804.03720","title":"Gotta Learn Fast: A New Benchmark for Generalization in RL","created":"2018-04-10","cited_by_count":59},{"id":"2306.09884","title":"Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX","created":"2023-06-16","cited_by_count":58},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49},{"id":"2312.15224","title":"LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination","created":"2023-12-23","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":"2106.10853","title":"On the Importance of Environments in Human-Robot Coordination","created":"2021-06-21","cited_by_count":37},{"id":"2302.01605","title":"Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased","created":"2023-02-03","cited_by_count":37},{"id":"2303.03376","title":"MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning","created":"2023-03-06","cited_by_count":31},{"id":"2302.04831","title":"Cooperative Open-ended Learning Framework for Zero-shot Coordination","created":"2023-02-09","cited_by_count":30},{"id":"2101.05507","title":"Evaluating the Robustness of Collaborative Agents","created":"2021-01-14","cited_by_count":25},{"id":"2001.09908","title":"Rotation, Translation, and Cropping for Zero-Shot Generalization","created":"2020-01-27","cited_by_count":24},{"id":"2310.05208","title":"ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination","created":"2023-10-08","cited_by_count":24},{"id":"1811.05939","title":"Domain Randomization for Scene-Specific Car Detection and Pose Estimation","created":"2018-11-14","cited_by_count":23},{"id":"1901.01291","title":"On the Utility of Model Learning in HRI","created":"2019-01-04","cited_by_count":21},{"id":"2102.09812","title":"Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space","created":"2021-02-19","cited_by_count":20},{"id":"2110.07594","title":"The Neural MMO Platform for Massively Multiagent Research","created":"2021-10-14","cited_by_count":17},{"id":"2308.10797","title":"Stabilizing Unsupervised Environment Design with a Learned Adversary","created":"2023-08-21","cited_by_count":17},{"id":"2111.04051","title":"Coordinated Proximal Policy Optimization","created":"2021-11-07","cited_by_count":16},{"id":"2403.11075","title":"GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment","created":"2024-03-17","cited_by_count":16},{"id":"2403.13091","title":"JaxUED: A simple and useable UED library in Jax","created":"2024-03-19","cited_by_count":11},{"id":"1910.08809","title":"A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning","created":"2019-10-19","cited_by_count":10},{"id":"2311.12716","title":"minimax: Efficient Baselines for Autocurricula in JAX","created":"2023-11-21","cited_by_count":10},{"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":"2301.08025","title":"Generalization through Diversity: Improving Unsupervised Environment Design","created":"2023-01-19","cited_by_count":9},{"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":"2311.03736","title":"Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning","created":"2023-11-07","cited_by_count":9},{"id":"2211.01602","title":"Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration","created":"2022-11-03","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":"2404.17780","title":"Verco: Learning Coordinated Verbal Communication for Multi-agent Reinforcement Learning","created":"2024-04-27","cited_by_count":7},{"id":"1812.00491","title":"Adversarial Domain Randomization","created":"2018-12-03","cited_by_count":5},{"id":"2405.03735","title":"Select to Perfect: Imitating desired behavior from large multi-agent data","created":"2024-05-06","cited_by_count":4},{"id":"2302.04944","title":"Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition","created":"2023-02-09","cited_by_count":3},{"id":"2310.07218","title":"Quantifying Agent Interaction in Multi-agent Reinforcement Learning for Cost-efficient Generalization","created":"2023-10-11","cited_by_count":2}],"next_cursor":null}