{"total":43,"rows":[{"id":"2403.10506","title":"HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation","created":"2024-03-15","cited_by_count":112,"area":null},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63,"area":null},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59,"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":"2303.17503","title":"Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning","created":"2023-03-29","cited_by_count":51,"area":null},{"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":"2211.11260","title":"Discovering Evolution Strategies via Meta-Black-Box Optimization","created":"2022-11-21","cited_by_count":44,"area":null},{"id":"2212.04180","title":"evosax: JAX-based Evolution Strategies","created":"2022-12-08","cited_by_count":41,"area":null},{"id":"2304.03995","title":"Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization","created":"2023-04-08","cited_by_count":33,"area":null},{"id":"2301.13139","title":"A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence","created":"2023-01-30","cited_by_count":30,"area":null},{"id":"2511.16652","title":"Evolution Strategies at the Hyperscale","created":"2025-11-20","cited_by_count":25,"area":null},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2310.02782","title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design","created":"2023-10-04","cited_by_count":16,"area":null},{"id":"2308.13289","title":"JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading","created":"2023-08-25","cited_by_count":14,"area":null},{"id":"2302.01470","title":"Learning to Optimize for Reinforcement Learning","created":"2023-02-03","cited_by_count":12,"area":null},{"id":"2403.13091","title":"JaxUED: A simple and useable UED library in Jax","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2306.01460","title":"ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages","created":"2023-06-02","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":"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":"2310.04590","title":"Deep Model Predictive Optimization","created":"2023-10-06","cited_by_count":7,"area":null},{"id":"2509.22335","title":"Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2406.15042","title":"Behaviour Distillation","created":"2024-06-21","cited_by_count":5,"area":null},{"id":"2503.15703","title":"Predicting Multi-Agent Specialization via Task Parallelizability","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2303.09478","title":"Arbitrary Order Meta-Learning with Simple Population-Based Evolution","created":"2023-03-16","cited_by_count":4,"area":null},{"id":"2406.16424","title":"Memory-Enhanced Neural Solvers for Routing Problems","created":"2024-06-24","cited_by_count":4,"area":null},{"id":"2505.00793","title":"Scalable Meta-Learning via Mixed-Mode Differentiation","created":"2025-05-01","cited_by_count":4,"area":null},{"id":"2502.10906","title":"PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning","created":"2025-02-15","cited_by_count":3,"area":null},{"id":"2508.09193","title":"Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2508.15679","title":"An Efficient Open World Environment for Multi-Agent Social Learning","created":"2025-08-21","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":"2507.05561","title":"Preemptive Solving of Future Problems: Multitask Preplay in Humans and Machines","created":"2025-07-08","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":"2405.11397","title":"Preparing for Black Swans: The Antifragility Imperative for Machine Learning","created":"2024-05-18","cited_by_count":1,"area":null},{"id":"2406.01939","title":"Speeding up Policy Simulation in Supply Chain RL","created":"2024-06-04","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":"2602.11387","title":"Provably Efficient Algorithms for S- and Non-Rectangular Robust MDPs with General Parameterization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.19142","title":"Celo2: Towards Learned Optimization Free Lunch","created":"2026-02-22","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":"2403.14019","title":"Searching Search Spaces: Meta-evolving a Geometric Encoding for Neural Networks","created":"2024-03-20","cited_by_count":0,"area":null},{"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":"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":"2508.13326","title":"Decoding Communications with Partial Information","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2603.19864","title":"NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing","created":"2026-03-20","cited_by_count":0,"area":null}],"next_cursor":null}