{"total":51,"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":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63,"area":null},{"id":"2407.17032","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","created":"2024-07-24","cited_by_count":46,"area":"deeprl"},{"id":"2410.23208","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","created":"2024-10-30","cited_by_count":45,"area":null},{"id":"2407.19396","title":"NAVIX: Scaling MiniGrid Environments with JAX","created":"2024-07-28","cited_by_count":18,"area":"deeprl"},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2506.03404","title":"The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks","created":"2025-06-03","cited_by_count":13,"area":"deeprl"},{"id":"2403.13091","title":"JaxUED: A simple and useable UED library in Jax","created":"2024-03-19","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":"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":"2510.06288","title":"BuilderBench: The Building Blocks of Intelligent Agents","created":"2025-10-07","cited_by_count":6,"area":"agents"},{"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":"2606.00151","title":"Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying","created":"2026-05-29","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":"2503.01450","title":"Investigating Memory in Model-Free RL with POPGym Arcade","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"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":"2402.18994","title":"Spyx: A Library for Just-In-Time Compiled Optimization of Spiking Neural Networks","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2510.18183","title":"NashPG: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria","created":"2025-10-21","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":"2606.06096","title":"OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation","created":"2026-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2606.26463","title":"Finding the Time to Think: Learning Planning Budgets in Real-Time RL","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2406.00424","title":"A Batch Sequential Halving Algorithm without Performance Degradation","created":"2024-06-01","cited_by_count":1,"area":null},{"id":"2410.22165","title":"EconoJax: A Fast & Scalable Economic Simulation in Jax","created":"2024-10-29","cited_by_count":1,"area":"deeprl"},{"id":"2501.15129","title":"EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning","created":"2025-01-25","cited_by_count":1,"area":"deeprl"},{"id":"2508.15693","title":"NiceWebRL: a Python library for human subject experiments with reinforcement learning environments","created":"2025-08-21","cited_by_count":1,"area":"alignment"},{"id":"2510.18221","title":"The Emergence of Complex Behavior in Large-Scale Ecological Environments","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2602.10894","title":"Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games","created":"2026-02-11","cited_by_count":1,"area":"deeprl"},{"id":"2605.09150","title":"AlphaExploitem: Going Beyond the Nash Equilibrium in Poker by Learning to Exploit Suboptimal Play","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.24515","title":"Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation","created":"2026-06-23","cited_by_count":1,"area":"agents"},{"id":"2406.10306","title":"A Simple, Solid, and Reproducible Baseline for Bridge Bidding AI","created":"2024-06-14","cited_by_count":0,"area":null},{"id":"2410.23753","title":"Enhancing Chess Reinforcement Learning with Graph Representation","created":"2024-10-31","cited_by_count":0,"area":"deeprl"},{"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":"2504.19625","title":"Rulebook: bringing co-routines to reinforcement learning environments","created":"2025-04-28","cited_by_count":0,"area":"deeprl"},{"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":"2507.01522","title":"Chargax: A JAX Accelerated EV Charging Simulator","created":"2025-07-02","cited_by_count":0,"area":"deeprl"},{"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":"2508.07522","title":"Evolutionary Optimization of Deep Learning Agents for Sparrow Mahjong","created":"2025-08-11","cited_by_count":0,"area":"deeprl"},{"id":"2512.21648","title":"Variance-Aware Prior-Based Tree Policies for Monte Carlo Tree Search","created":"2025-12-25","cited_by_count":0,"area":"deeprl"},{"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":"2603.12145","title":"Automatic Generation of High-Performance RL Environments","created":"2026-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2604.05476","title":"Reproducing AlphaZero on Tablut: Self-Play RL for an Asymmetric Board Game","created":"2026-04-07","cited_by_count":0,"area":"deeprl"},{"id":"2605.08982","title":"Particle Monte Carlo Tree Search","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2609.09094","title":"The Surprising Effectiveness of Approximate Value Iteration in Self-Play","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.11923","title":"GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay","created":"2026-09-10","cited_by_count":0,"area":null},{"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":"2610.01566","title":"Towards Optimal Policy Improvement","created":"2026-10-01","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":"2610.14883","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}