{"total":60,"rows":[{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468,"area":null},{"id":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55,"area":null},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49,"area":null},{"id":"2109.09180","title":"Lifelong Robotic Reinforcement Learning by Retaining Experiences","created":"2021-09-19","cited_by_count":34,"area":null},{"id":"2406.14325","title":"Reproducibility in Machine Learning-based Research: Overview, Barriers and Drivers","created":"2024-06-20","cited_by_count":34,"area":null},{"id":"2204.01403","title":"How stable are Transferability Metrics evaluations?","created":"2022-04-04","cited_by_count":30,"area":null},{"id":"2110.11222","title":"Is High Variance Unavoidable in RL? A Case Study in Continuous Control","created":"2021-10-21","cited_by_count":28,"area":null},{"id":"2202.02326","title":"Towards Training Reproducible Deep Learning Models","created":"2022-02-04","cited_by_count":23,"area":null},{"id":"2212.11110","title":"Lifelong Reinforcement Learning with Modulating Masks","created":"2022-12-21","cited_by_count":22,"area":null},{"id":"2103.09815","title":"TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL","created":"2021-03-17","cited_by_count":18,"area":null},{"id":"2406.16241","title":"Position: Benchmarking is Limited in Reinforcement Learning Research","created":"2024-06-23","cited_by_count":15,"area":"deeprl"},{"id":"2504.02587","title":"Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme","created":"2025-04-03","cited_by_count":14,"area":"lr"},{"id":"2606.03108","title":"EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning","created":"2026-06-02","cited_by_count":14,"area":"agents"},{"id":"2301.07799","title":"A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems","created":"2023-01-18","cited_by_count":13,"area":null},{"id":"2502.19652","title":"Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning","created":"2025-02-27","cited_by_count":13,"area":"deeprl"},{"id":"2305.10997","title":"Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2501.15893","title":"Benchmarking Quantum Reinforcement Learning","created":"2025-01-27","cited_by_count":10,"area":"deeprl"},{"id":"2105.12991","title":"Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization","created":"2021-05-27","cited_by_count":8,"area":null},{"id":"2402.03590","title":"Assessing the Impact of Distribution Shift on Reinforcement Learning Performance","created":"2024-02-05","cited_by_count":7,"area":"deeprl"},{"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":"2110.14468","title":"DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention","created":"2021-10-27","cited_by_count":4,"area":null},{"id":"2303.11634","title":"Deep Q-Network Based Decision Making for Autonomous Driving","created":"2023-03-21","cited_by_count":4,"area":"driving"},{"id":"2310.00229","title":"Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2602.08690","title":"SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity","created":"2026-02-09","cited_by_count":4,"area":"deeprl"},{"id":"2604.07799","title":"Evolving Skill Modules under a Fixed Planner: Versioning, Rollback, and Runtime Governance for Long-Lived Robot Systems","created":"2026-04-09","cited_by_count":4,"area":null},{"id":"2306.10882","title":"AdaStop: adaptive statistical testing for sound comparisons of Deep RL agents","created":"2023-06-19","cited_by_count":3,"area":null},{"id":"2406.02890","title":"Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2409.19231","title":"Double Actor-Critic with TD Error-Driven Regularization in Reinforcement Learning","created":"2024-09-28","cited_by_count":3,"area":"deeprl"},{"id":"2501.17115","title":"Evidence on the Regularisation Properties of Maximum-Entropy Reinforcement Learning","created":"2025-01-28","cited_by_count":3,"area":"deeprl"},{"id":"2510.06730","title":"PTEB: Towards Robust Text Embedding Evaluation via Stochastic Paraphrasing at Evaluation Time with LLMs","created":"2025-10-08","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":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2407.18840","title":"The Cross-environment Hyperparameter Setting Benchmark for Reinforcement Learning","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2503.03056","title":"A2Perf: Real-World Autonomous Agents Benchmark","created":"2025-03-04","cited_by_count":2,"area":"offlinerl"},{"id":"2606.00135","title":"On Effectiveness and Efficiency of Agentic Tool-calling and RL Training","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2606.06746","title":"Performance Variation in Deep Reinforcement Learning","created":"2026-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2312.08463","title":"How much can change in a year? Revisiting Evaluation in Multi-Agent Reinforcement Learning","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2505.12006","title":"SOCIA-$\\nabla$: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation","created":"2025-05-17","cited_by_count":1,"area":"agents"},{"id":"2506.05577","title":"Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systems","created":"2025-06-05","cited_by_count":1,"area":"agents"},{"id":"2601.10905","title":"Action Shapley: A Training Data Selection Metric for World Model in Reinforcement Learning","created":"2026-01-15","cited_by_count":1,"area":"wm"},{"id":"2605.21214","title":"Behavior-Consistent Deep Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"id":"2505.15306","title":"Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One","created":"2025-05-21","cited_by_count":0,"area":"agents"},{"id":"2510.18551","title":"SOCIA-Nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation","created":"2025-10-21","cited_by_count":0,"area":"agents"},{"id":"2512.24145","title":"When Does Pairing Seeds Reduce Variance? Evidence from a Multi-Agent Economic Simulation","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2604.17351","title":"SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.21282","title":"Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent","created":"2026-05-20","cited_by_count":0,"area":"deeprl"},{"id":"2607.05985","title":"Auto-DSM Under the Lens: A Black-Box Evaluation Framework for LLM-Based DSM Generation","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2609.05508","title":"When Do Options Help? Policy Necrosis and Redundant Coverage in Option-Critic","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.25152","title":"Exposing Blind Spots in Deep Imbalanced Regression Evaluation","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.37085","title":"ARGOS: Reinforcement Learning-Driven Multidimensional Elasticity for Service Orchestration in the Computing Continuum","created":"2026-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2609.37294","title":"SafeLLM4SE: Statistical Evaluation and Reporting for LLM-based Software Engineering Systems","created":"2026-09-29","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":"2609.39901","title":"Do Better Goal Representations Improve Goal-Conditioned Reinforcement Learning?","created":"2026-09-30","cited_by_count":0,"area":"deeprl"},{"id":"2610.01224","title":"Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning","created":"2026-10-01","cited_by_count":0,"area":"wm"},{"id":"2610.03119","title":"How to Find and Reuse Policies for Continuous Adaptation in Lifelong Reinforcement Learning","created":"2026-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2610.04810","title":"Separating Decision Time from Decision Quality in the Real-Time Gap of Distilled Deciders: Evidence from a Game and a Conveyor Simulator","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.07594","title":"BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation","created":"2026-10-06","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}