{"total":63,"rows":[{"id":"2402.16801","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","created":"2024-02-26","cited_by_count":88,"area":"deeprl"},{"id":"2408.01584","title":"GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS","created":"2024-08-02","cited_by_count":45,"area":"driving"},{"id":"2503.14858","title":"1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities","created":"2025-03-19","cited_by_count":45,"area":"deeprl"},{"id":"2312.01472","title":"BenchMARL: Benchmarking Multi-Agent Reinforcement Learning","created":"2023-12-03","cited_by_count":33,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2502.12272","title":"Learning to Reason at the Frontier of Learnability","created":"2025-02-17","cited_by_count":23,"area":"lr"},{"id":"2312.12568","title":"Scaling Opponent Shaping to High Dimensional Games","created":"2023-12-19","cited_by_count":12,"area":null},{"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,"area":"deeprl"},{"id":"2412.04233","title":"HyperMARL: Adaptive Hypernetworks for Multi-Agent RL","created":"2024-12-05","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":"2311.12716","title":"minimax: Efficient Baselines for Autocurricula in JAX","created":"2023-11-21","cited_by_count":10,"area":null},{"id":"2409.00853","title":"JaxLife: An Open-Ended Agentic Simulator","created":"2024-09-01","cited_by_count":6,"area":"agents"},{"id":"2505.23686","title":"ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2506.02387","title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","created":"2025-06-03","cited_by_count":6,"area":"mllm"},{"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":"2505.17323","title":"Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2501.06058","title":"Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot Coordination","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2508.12480","title":"The Yokai Learning Environment: Tracking Beliefs Over Space and Time","created":"2025-08-17","cited_by_count":3,"area":null},{"id":"2509.10656","title":"Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration","created":"2025-09-12","cited_by_count":3,"area":null},{"id":"2511.16592","title":"gfnx: Fast and Scalable Library for Generative Flow Networks in JAX","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2407.12505","title":"Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments","created":"2024-07-17","cited_by_count":2,"area":"deeprl"},{"id":"2407.14516","title":"RobocupGym: A challenging continuous control benchmark in Robocup","created":"2024-07-03","cited_by_count":2,"area":"deeprl"},{"id":"2511.04904","title":"Multi-Agent Craftax: Benchmarking Open-Ended Multi-Agent Reinforcement Learning at the Hyperscale","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2512.06102","title":"JaxWildfire: A GPU-Accelerated Wildfire Simulator for Reinforcement Learning","created":"2025-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2605.11688","title":"Shaping Zero-Shot Coordination via State Blocking","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.24423","title":"Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork","created":"2026-05-23","cited_by_count":2,"area":"deeprl"},{"id":"2606.08340","title":"Benchmarking Open-Ended Multi-Agent Coordination in Language Agents","created":"2026-06-06","cited_by_count":2,"area":"agents"},{"id":"2606.20376","title":"CRAX: Fast Safe Reinforcement Learning Benchmarking","created":"2026-06-18","cited_by_count":2,"area":"deeprl"},{"id":"2406.00424","title":"A Batch Sequential Halving Algorithm without Performance Degradation","created":"2024-06-01","cited_by_count":1,"area":null},{"id":"2501.15129","title":"EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning","created":"2025-01-25","cited_by_count":1,"area":"deeprl"},{"id":"2505.10484","title":"Fixing Incomplete Value Function Decomposition for Multi-Agent Reinforcement Learning","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2510.04862","title":"Video Game Level Design as a Multi-Agent Reinforcement Learning Problem","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2511.02304","title":"Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2511.04177","title":"When Assisting One Disempowers Another","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2602.08965","title":"Learning to Coordinate via Quantum Entanglement in Multi-Agent Reinforcement Learning","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2605.07101","title":"Decentralized Diffusion Policy Learning for Enhanced Exploration in Cooperative Multi-agent Reinforcement Learning","created":"2026-05-08","cited_by_count":1,"area":"diffusion"},{"id":"2606.01478","title":"Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2609.13716","title":"JaxAHT: A JAX-Based Library for Ad Hoc Teamwork","created":"2026-09-12","cited_by_count":1,"area":null},{"id":"2404.03101","title":"MARL-LNS: Cooperative Multi-agent Reinforcement Learning via Large Neighborhoods Search","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2410.15876","title":"FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2412.16970","title":"A Research Agenda for Usability and Generalisation in Reinforcement Learning","created":"2024-12-22","cited_by_count":0,"area":"deeprl"},{"id":"2505.22151","title":"Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARL","created":"2025-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2507.21638","title":"Assistax: A Multi-Agent Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotics","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2512.24827","title":"Inter-Agent Relative Representations for Multi-Agent Option Discovery","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2602.01665","title":"TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.20141","title":"Recurrent Structural Policy Gradient for Partially Observable Mean Field Games","created":"2026-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2603.01260","title":"MOSAIC: A Universal Agent-Level Interface for Cross-Paradigm Agent Mixing and Human-AI Collaboration","created":"2026-03-01","cited_by_count":0,"area":"agents"},{"id":"2603.09208","title":"Strategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.12145","title":"Automatic Generation of High-Performance RL Environments","created":"2026-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2603.19864","title":"NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.15044","title":"CoGrid & the Multi-User Gymnasium: A Framework for Multi-Agent Experimentation","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.01865","title":"Quality-Aware Exploration Budget Allocation for Cooperative Multi-Agent Reinforcement Learning","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.09212","title":"Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.13554","title":"Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.20255","title":"Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty","created":"2026-05-18","cited_by_count":0,"area":"driving"},{"id":"2605.31361","title":"Dreaming Of Others: Latent Teammate Modeling In World Models For Multi-Agent Reinforcement Learning","created":"2026-05-29","cited_by_count":0,"area":"wm"},{"id":"2609.02459","title":"CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.03667","title":"Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning","created":"2026-09-03","cited_by_count":0,"area":"offlinerl"},{"id":"2609.36052","title":"PowerZooJax: A JAX-based Power System Benchmark for Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2609.38065","title":"Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RL","created":"2026-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2610.05569","title":"Factoriax: A GPU-Accelerated Factorio-Style Simulator for Reinforcement Learning","created":"2026-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2610.07686","title":"BluffJAX: Adversarial Imperfect Information Games in JAX","created":"2026-10-06","cited_by_count":0,"area":"deeprl"},{"id":"2610.14883","title":"MARL-BattleGrounds: A Novel JAX-native Benchmark for Heterogeneous and Competitive Multi-agent RL","created":"2026-10-10","cited_by_count":0,"area":"agents"}],"next_cursor":null}