{"total":58,"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":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2306.17100","title":"RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","created":"2023-06-29","cited_by_count":71,"area":null},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"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":"2407.14931","title":"POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding","created":"2024-07-20","cited_by_count":21,"area":null},{"id":"2308.03665","title":"QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration","created":"2023-08-07","cited_by_count":17,"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":"2505.16952","title":"FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization","created":"2025-05-22","cited_by_count":11,"area":null},{"id":"2507.23172","title":"Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks","created":"2025-07-31","cited_by_count":11,"area":"deeprl"},{"id":"2311.12716","title":"minimax: Efficient Baselines for Autocurricula in JAX","created":"2023-11-21","cited_by_count":10,"area":null},{"id":"2410.01706","title":"Sable: a Performant, Efficient and Scalable Sequence Model for MARL","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2410.22093","title":"PC-Gym: Benchmark Environments For Process Control Problems","created":"2024-10-29","cited_by_count":10,"area":"deeprl"},{"id":"2503.14576","title":"SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2025-03-18","cited_by_count":8,"area":null},{"id":"2407.07333","title":"Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy","created":"2024-07-10","cited_by_count":7,"area":"deeprl"},{"id":"2409.03811","title":"PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization","created":"2024-09-05","cited_by_count":7,"area":null},{"id":"2504.06048","title":"Trust-Region Twisted Policy Improvement","created":"2025-04-08","cited_by_count":6,"area":"deeprl"},{"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":"2510.06288","title":"BuilderBench: The Building Blocks of Intelligent Agents","created":"2025-10-07","cited_by_count":6,"area":"agents"},{"id":"2402.07963","title":"SPO: Sequential Monte Carlo Policy Optimisation","created":"2024-02-12","cited_by_count":5,"area":null},{"id":"2510.01764","title":"Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAX","created":"2025-10-02","cited_by_count":5,"area":"deeprl"},{"id":"2508.16821","title":"PuzzleJAX: A Benchmark for Reasoning and Learning","created":"2025-08-22","cited_by_count":4,"area":"lr"},{"id":"2406.12589","title":"Discovering Minimal Reinforcement Learning Environments","created":"2024-06-18","cited_by_count":3,"area":"deeprl"},{"id":"2411.00666","title":"Beyond the Boundaries of Proximal Policy Optimization","created":"2024-11-01","cited_by_count":3,"area":"deeprl"},{"id":"2503.01450","title":"Investigating Memory in Model-Free RL with POPGym Arcade","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"id":"2508.06336","title":"Unsupervised Partner Design Enables Robust Ad-hoc Teamwork","created":"2025-08-08","cited_by_count":3,"area":"deeprl"},{"id":"2511.14220","title":"Twice Sequential Monte Carlo for Tree Search","created":"2025-11-18","cited_by_count":3,"area":"deeprl"},{"id":"2603.06413","title":"A Reference Architecture of Reinforcement Learning Frameworks","created":"2026-03-06","cited_by_count":3,"area":"deeprl"},{"id":"2503.03056","title":"A2Perf: Real-World Autonomous Agents Benchmark","created":"2025-03-04","cited_by_count":2,"area":"offlinerl"},{"id":"2508.12845","title":"CAMAR: Continuous Actions Multi-Agent Routing","created":"2025-08-18","cited_by_count":2,"area":null},{"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":"2606.20376","title":"CRAX: Fast Safe Reinforcement Learning Benchmarking","created":"2026-06-18","cited_by_count":2,"area":"deeprl"},{"id":"2405.11457","title":"Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice","created":"2024-05-19","cited_by_count":1,"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":"2605.11355","title":"gym-invmgmt: An Open Benchmarking Framework for Inventory Management Methods","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.28433","title":"Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy","created":"2026-06-26","cited_by_count":1,"area":"deeprl"},{"id":"2609.13716","title":"JaxAHT: A JAX-Based Library for Ad Hoc Teamwork","created":"2026-09-12","cited_by_count":1,"area":null},{"id":"2308.08693","title":"AI planning in the imagination: High-level planning on learned abstract search spaces","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2411.14411","title":"Multi-Agent Environments for Vehicle Routing Problems","created":"2024-11-21","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":"2504.05112","title":"ABCDWaveNet: Advancing Robust Road Ponding Detection in Fog through Dynamic Frequency-Spatial Synergy","created":"2025-04-07","cited_by_count":0,"area":null},{"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":"2506.22609","title":"Ludax: A GPU-Accelerated Domain Specific Language for Board Games","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2601.14232","title":"KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning","created":"2026-01-20","cited_by_count":0,"area":"deeprl"},{"id":"2601.17564","title":"JaxARC: A High-Performance JAX-based Environment for Abstraction and Reasoning Research","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2605.08982","title":"Particle Monte Carlo Tree Search","created":"2026-05-09","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":"2606.14130","title":"Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.14180","title":"RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences","created":"2026-07-15","cited_by_count":0,"area":"wm"},{"id":"2607.29577","title":"DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combat","created":"2026-07-31","cited_by_count":0,"area":null},{"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":"2609.09059","title":"PlayTrain: An Efficient Reinforcement Learning Framework for LLM-Generated Adaptable JavaScript Games","created":"2026-09-08","cited_by_count":0,"area":null},{"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":"2610.19051","title":"Smart Alone, Blind Together: Why Accuracy Fails to CertifyTheory of Mind in Multi-Agent Teams","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}