{"total":313,"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":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345,"area":"offlinerl"},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"area":"alignment"},{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302,"area":"agents"},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237,"area":"agents"},{"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":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222,"area":null},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182,"area":null},{"id":"2106.04895","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","created":"2021-06-09","cited_by_count":158,"area":"offlinerl"},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133,"area":null},{"id":"2110.14555","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","created":"2021-10-27","cited_by_count":114,"area":null},{"id":"2206.13353","title":"Is Power-Seeking AI an Existential Risk?","created":"2022-06-16","cited_by_count":105,"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":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"area":null},{"id":"2505.02077","title":"Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents","created":"2025-05-04","cited_by_count":71,"area":"safety"},{"id":"2207.03530","title":"VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning","created":"2022-07-07","cited_by_count":68,"area":null},{"id":"2110.04184","title":"When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?","created":"2021-10-08","cited_by_count":67,"area":null},{"id":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63,"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":"2405.18540","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","created":"2024-05-28","cited_by_count":54,"area":"safety"},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2511.07317","title":"RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments","created":"2025-11-10","cited_by_count":50,"area":null},{"id":"2404.10775","title":"COMBO: Compositional World Models for Embodied Multi-Agent Cooperation","created":"2024-04-16","cited_by_count":49,"area":"wm"},{"id":"2106.03352","title":"The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces","created":"2021-06-07","cited_by_count":48,"area":null},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2410.08115","title":"Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System","created":"2024-10-10","cited_by_count":43,"area":"agents"},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40,"area":null},{"id":"2103.07927","title":"Modelling Behavioural Diversity for Learning in Open-Ended Games","created":"2021-03-14","cited_by_count":39,"area":null},{"id":"2103.15819","title":"Augmenting Automated Game Testing with Deep Reinforcement Learning","created":"2021-03-29","cited_by_count":38,"area":null},{"id":"2103.04564","title":"Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization","created":"2021-03-08","cited_by_count":35,"area":null},{"id":"2210.12631","title":"LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulation","created":"2022-10-23","cited_by_count":34,"area":null},{"id":"2110.13827","title":"Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization","created":"2021-10-26","cited_by_count":33,"area":null},{"id":"2209.13900","title":"Disentangling Transfer in Continual Reinforcement Learning","created":"2022-09-28","cited_by_count":33,"area":null},{"id":"2301.13261","title":"Emergence of Maps in the Memories of Blind Navigation Agents","created":"2023-01-30","cited_by_count":33,"area":null},{"id":"2206.07505","title":"Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2303.03376","title":"MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning","created":"2023-03-06","cited_by_count":31,"area":null},{"id":"2106.10110","title":"Towards Distraction-Robust Active Visual Tracking","created":"2021-06-18","cited_by_count":30,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2302.06606","title":"Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation","created":"2023-02-13","cited_by_count":30,"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":"2111.04613","title":"Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems","created":"2021-11-08","cited_by_count":26,"area":null},{"id":"2106.05262","title":"TempoRL: Learning When to Act","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2102.07659","title":"Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems","created":"2021-02-15","cited_by_count":24,"area":null},{"id":"2307.07871","title":"The SocialAI School: Insights from Developmental Psychology Towards Artificial Socio-Cultural Agents","created":"2023-07-15","cited_by_count":24,"area":"agents"},{"id":"2204.02246","title":"Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization","created":"2022-04-04","cited_by_count":23,"area":null},{"id":"2502.19559","title":"Stay Focused: Problem Drift in Multi-Agent Debate","created":"2025-02-26","cited_by_count":23,"area":"agents"},{"id":"2103.01933","title":"PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception","created":"2021-03-02","cited_by_count":22,"area":null},{"id":"2203.13733","title":"Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning","created":"2022-03-15","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":"2210.13708","title":"MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library","created":"2022-10-11","cited_by_count":21,"area":null},{"id":"2407.14931","title":"POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding","created":"2024-07-20","cited_by_count":21,"area":null},{"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,"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":"2302.10418","title":"MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization","created":"2023-02-21","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":"2103.07607","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","created":"2021-03-13","cited_by_count":19,"area":null},{"id":"2507.05619","title":"Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests","created":"2025-07-08","cited_by_count":19,"area":"alignment"},{"id":"2209.10113","title":"Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning","created":"2022-09-20","cited_by_count":18,"area":null},{"id":"2408.02871","title":"Hide and Seek: Fingerprinting Large Language Models with Evolutionary Learning","created":"2024-08-06","cited_by_count":18,"area":null},{"id":"2104.06922","title":"Safe Continuous Control with Constrained Model-Based Policy Optimization","created":"2021-04-14","cited_by_count":17,"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":"2203.06803","title":"Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits","created":"2022-03-14","cited_by_count":17,"area":null},{"id":"2405.02425","title":"Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning","created":"2024-05-03","cited_by_count":17,"area":"deeprl"},{"id":"2407.03302","title":"A Review of the Applications of Deep Learning-Based Emergent Communication","created":"2024-07-03","cited_by_count":17,"area":"deeprl"},{"id":"2309.17207","title":"Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents","created":"2023-09-29","cited_by_count":16,"area":null},{"id":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16,"area":"alignment"},{"id":"2411.01775","title":"Eurekaverse: Environment Curriculum Generation via Large Language Models","created":"2024-11-04","cited_by_count":16,"area":null},{"id":"2404.10740","title":"N-Agent Ad Hoc Teamwork","created":"2024-04-16","cited_by_count":15,"area":"deeprl"},{"id":"2202.10608","title":"It Takes Four to Tango: Multiagent Selfplay for Automatic Curriculum Generation","created":"2022-02-22","cited_by_count":14,"area":null},{"id":"2206.06282","title":"Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Tasks","created":"2022-06-13","cited_by_count":14,"area":null},{"id":"2210.02506","title":"Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors","created":"2022-10-05","cited_by_count":14,"area":null},{"id":"2304.12000","title":"Hierarchical State Abstraction Based on Structural Information Principles","created":"2023-04-24","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":"2504.21048","title":"Multi-Agent Reinforcement Learning for Resources Allocation Optimization: A Survey","created":"2025-04-29","cited_by_count":14,"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":"2411.01796","title":"Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge","created":"2024-11-04","cited_by_count":13,"area":null},{"id":"2304.00755","title":"Effective and Stable Role-Based Multi-Agent Collaboration by Structural Information Principles","created":"2023-04-03","cited_by_count":12,"area":null},{"id":"2407.08590","title":"A Review of Nine Physics Engines for Reinforcement Learning Research","created":"2024-07-11","cited_by_count":12,"area":"deeprl"},{"id":"2512.03318","title":"Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia","created":"2025-12-03","cited_by_count":12,"area":"agents"},{"id":"2512.16856","title":"Distributional AGI Safety","created":"2025-12-18","cited_by_count":12,"area":null},{"id":"2102.05628","title":"On the Regularity of Attention","created":"2021-02-10","cited_by_count":11,"area":null},{"id":"2102.08431","title":"Complex Momentum for Optimization in Games","created":"2021-02-16","cited_by_count":11,"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":"2207.05683","title":"Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL","created":"2022-06-01","cited_by_count":11,"area":null},{"id":"2207.13649","title":"Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes","created":"2022-07-27","cited_by_count":11,"area":null},{"id":"2103.16511","title":"Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World","created":"2021-03-30","cited_by_count":10,"area":null},{"id":"2111.05992","title":"On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning","created":"2021-11-10","cited_by_count":10,"area":null},{"id":"2201.01221","title":"A Deeper Understanding of State-Based Critics in Multi-Agent Reinforcement Learning","created":"2022-01-03","cited_by_count":10,"area":null},{"id":"2205.11104","title":"Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2307.07670","title":"Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning","created":"2023-07-15","cited_by_count":10,"area":null},{"id":"2307.09470","title":"Multi-Player Zero-Sum Markov Games with Networked Separable Interactions","created":"2023-07-13","cited_by_count":10,"area":null},{"id":"2310.08549","title":"Cross-Episodic Curriculum for Transformer Agents","created":"2023-10-12","cited_by_count":10,"area":null},{"id":"2311.12716","title":"minimax: Efficient Baselines for Autocurricula in JAX","created":"2023-11-21","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}],"next_cursor":"100"}