{"total":104,"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":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111,"area":"ssm"},{"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":"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":"2406.08414","title":"Discovering Preference Optimization Algorithms with and for Large Language Models","created":"2024-06-12","cited_by_count":42,"area":"alignment"},{"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":"2408.15099","title":"No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery","created":"2024-08-27","cited_by_count":31,"area":"deeprl"},{"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":"2401.11963","title":"Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms","created":"2024-01-22","cited_by_count":26,"area":"deeprl"},{"id":"2511.16652","title":"Evolution Strategies at the Hyperscale","created":"2025-11-20","cited_by_count":25,"area":null},{"id":"2406.17523","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning","created":"2024-06-25","cited_by_count":21,"area":"deeprl"},{"id":"2406.18420","title":"Mixture of Experts in a Mixture of RL settings","created":"2024-06-26","cited_by_count":21,"area":"moe"},{"id":"2402.05828","title":"Discovering Temporally-Aware Reinforcement Learning Algorithms","created":"2024-02-08","cited_by_count":18,"area":"deeprl"},{"id":"2402.12284","title":"Refining Minimax Regret for Unsupervised Environment Design","created":"2024-02-19","cited_by_count":18,"area":"deeprl"},{"id":"2407.19396","title":"NAVIX: Scaling MiniGrid Environments with JAX","created":"2024-07-28","cited_by_count":18,"area":"deeprl"},{"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":"2412.07165","title":"A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning","created":"2024-12-10","cited_by_count":15,"area":"deeprl"},{"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":"2407.07082","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","created":"2024-07-09","cited_by_count":14,"area":"deeprl"},{"id":"2502.01591","title":"Improving Transformer World Models for Data-Efficient RL","created":"2025-02-03","cited_by_count":13,"area":"wm"},{"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":"2412.17113","title":"Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps","created":"2024-12-22","cited_by_count":11,"area":"deeprl"},{"id":"2504.11453","title":"A Clean Slate for Offline Reinforcement Learning","created":"2025-04-15","cited_by_count":11,"area":"offlinerl"},{"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":"2409.01449","title":"Real-Time Recurrent Learning using Trace Units in Reinforcement Learning","created":"2024-09-02","cited_by_count":10,"area":"deeprl"},{"id":"2406.00392","title":"Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning","created":"2024-06-01","cited_by_count":8,"area":"deeprl"},{"id":"2406.11905","title":"EvIL: Evolution Strategies for Generalisable Imitation Learning","created":"2024-06-15","cited_by_count":8,"area":"offlinerl"},{"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":"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":"2408.12525","title":"PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generators","created":"2024-08-22","cited_by_count":7,"area":"deeprl"},{"id":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2507.11019","title":"Relative Entropy Pathwise Policy Optimization","created":"2025-07-15","cited_by_count":7,"area":"deeprl"},{"id":"2508.00046","title":"Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable Domains","created":"2025-07-31","cited_by_count":7,"area":"deeprl"},{"id":"2402.09900","title":"Recurrent Reinforcement Learning with Memoroids","created":"2024-02-15","cited_by_count":6,"area":"deeprl"},{"id":"2409.00853","title":"JaxLife: An Open-Ended Agentic Simulator","created":"2024-09-01","cited_by_count":6,"area":"agents"},{"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":"2507.17668","title":"How Should We Meta-Learn Reinforcement Learning Algorithms?","created":"2025-07-23","cited_by_count":5,"area":"deeprl"},{"id":"2508.06659","title":"In-Context Reinforcement Learning via Communicative World Models","created":"2025-08-08","cited_by_count":5,"area":"wm"},{"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":"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":"2410.20990","title":"Reference-Free Formula Drift with Reinforcement Learning: From Driving Data to Tire Energy-Inspired, Real-World Policies","created":"2024-10-28","cited_by_count":4,"area":"driving"},{"id":"2503.12358","title":"IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generation","created":"2025-03-16","cited_by_count":4,"area":"deeprl"},{"id":"2505.00793","title":"Scalable Meta-Learning via Mixed-Mode Differentiation","created":"2025-05-01","cited_by_count":4,"area":null},{"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":"2407.04221","title":"Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents","created":"2024-07-05","cited_by_count":3,"area":"offlinerl"},{"id":"2410.18519","title":"Reinforcement Learning Controllers for Soft Robots using Learned Environments","created":"2024-10-24","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":"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":"2503.01450","title":"Investigating Memory in Model-Free RL with POPGym Arcade","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"id":"2505.11714","title":"Bi-Level Policy Optimization with Nystr\\\"om Hypergradients","created":"2025-05-16","cited_by_count":3,"area":"deeprl"},{"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":"2411.06568","title":"Meta-Learning Objectives for Preference Optimization","created":"2024-11-10","cited_by_count":2,"area":"alignment"},{"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":"2512.06102","title":"JaxWildfire: A GPU-Accelerated Wildfire Simulator for Reinforcement Learning","created":"2025-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2402.05187","title":"Learning mirror maps in policy mirror descent","created":"2024-02-07","cited_by_count":1,"area":"deeprl"},{"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":"2505.18591","title":"Bayesian Meta-Reinforcement Learning with Laplace Variational Recurrent Networks","created":"2025-05-24","cited_by_count":1,"area":"deeprl"},{"id":"2507.04406","title":"Convergence and Sample Complexity of First-Order Methods for Agnostic Reinforcement Learning","created":"2025-07-06","cited_by_count":1,"area":"deeprl"},{"id":"2507.08718","title":"On the Effect of Regularization in Policy Mirror Descent","created":"2025-07-11","cited_by_count":1,"area":"deeprl"},{"id":"2508.07452","title":"Stackelberg Coupling of Online Representation Learning and Reinforcement Learning","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2508.10520","title":"Nonlocal Monte Carlo via Reinforcement Learning","created":"2025-08-14","cited_by_count":1,"area":"deeprl"},{"id":"2510.00922","title":"On Discovering Algorithms for Adversarial Imitation Learning","created":"2025-10-01","cited_by_count":1,"area":"offlinerl"},{"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":"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":"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":"2405.13609","title":"Tackling Decision Processes with Non-Cumulative Objectives using Reinforcement Learning","created":"2024-05-22","cited_by_count":0,"area":"deeprl"},{"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":"2507.01522","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":"2508.13326","title":"Decoding Communications with Partial Information","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2509.19464","title":"Evaluation-Aware Reinforcement Learning","created":"2025-09-23","cited_by_count":0,"area":"deeprl"},{"id":"2601.01803","title":"Moments Matter:Stabilizing Policy Optimization using Return Distributions","created":"2026-01-05","cited_by_count":0,"area":"deeprl"},{"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":"2603.12145","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":"2605.05481","title":"Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL","created":"2026-05-06","cited_by_count":0,"area":"deeprl"},{"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":"2605.19926","title":"JAXenstein: Accelerated Benchmarking for First-Person Environments","created":"2026-05-19","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}