{"total":55,"rows":[{"id":"2310.11324","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting","created":"2023-10-17","cited_by_count":817,"area":null},{"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":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2207.07048","title":"Leakage and the Reproducibility Crisis in ML-based Science","created":"2022-07-14","cited_by_count":65,"area":null},{"id":"2102.13651","title":"On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning","created":"2021-02-26","cited_by_count":59,"area":null},{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"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":"2103.04514","title":"Nondeterminism and Instability in Neural Network Optimization","created":"2021-03-08","cited_by_count":48,"area":null},{"id":"2201.08430","title":"Reproducibility in Learning","created":"2022-01-20","cited_by_count":44,"area":null},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36,"area":null},{"id":"2102.10264","title":"On Proximal Policy Optimization's Heavy-tailed Gradients","created":"2021-02-20","cited_by_count":31,"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":"2210.01542","title":"Hyperbolic Deep Reinforcement Learning","created":"2022-10-04","cited_by_count":25,"area":null},{"id":"2305.15284","title":"Replicable Reinforcement Learning","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2110.03375","title":"Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning","created":"2021-10-07","cited_by_count":18,"area":null},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2308.07832","title":"REFORMS: Reporting Standards for Machine Learning Based Science","created":"2023-08-15","cited_by_count":13,"area":null},{"id":"2211.06625","title":"CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality","created":"2022-11-12","cited_by_count":12,"area":null},{"id":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","cited_by_count":12,"area":null},{"id":"2407.10239","title":"What is Reproducibility in Artificial Intelligence and Machine Learning Research?","created":"2024-04-29","cited_by_count":11,"area":null},{"id":"2110.04935","title":"Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning","created":"2021-10-11","cited_by_count":10,"area":null},{"id":"2106.05526","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","created":"2021-06-10","cited_by_count":9,"area":null},{"id":"2309.15293","title":"Maximum diffusion reinforcement learning","created":"2023-09-26","cited_by_count":9,"area":null},{"id":"2404.11288","title":"A Preference-driven Paradigm for Enhanced Translation with Large Language Models","created":"2024-04-17","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2106.15883","title":"Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL","created":"2021-06-30","cited_by_count":8,"area":null},{"id":"2302.12691","title":"Reproducibility of Machine Learning: Terminology, Recommendations and Open Issues","created":"2023-02-24","cited_by_count":8,"area":null},{"id":"2304.02396","title":"AutoRL Hyperparameter Landscapes","created":"2023-04-05","cited_by_count":8,"area":null},{"id":"2111.09159","title":"Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance","created":"2021-11-17","cited_by_count":7,"area":null},{"id":"2201.11182","title":"Hyperparameter Tuning for Deep Reinforcement Learning Applications","created":"2022-01-26","cited_by_count":7,"area":null},{"id":"2206.11396","title":"Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learning","created":"2022-06-22","cited_by_count":7,"area":null},{"id":"2202.11452","title":"Deep Learning Reproducibility and Explainable AI (XAI)","created":"2022-02-23","cited_by_count":4,"area":null},{"id":"2212.10876","title":"Hyperparameters in Contextual RL are Highly Situational","created":"2022-12-21","cited_by_count":4,"area":null},{"id":"2102.11893","title":"Honey, I Shrunk The Actor: A Case Study on Preserving Performance with Smaller Actors in Actor-Critic RL","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2110.13079","title":"Which Model to Trust: Assessing the Influence of Models on the Performance of Reinforcement Learning Algorithms for Continuous Control Tasks","created":"2021-10-25","cited_by_count":3,"area":null},{"id":"2205.10416","title":"ARLO: A Framework for Automated Reinforcement Learning","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2504.04911","title":"IterMask3D: Unsupervised Anomaly Detection and Segmentation with Test-Time Iterative Mask Refinement in 3D Brain MR","created":"2025-04-07","cited_by_count":3,"area":null},{"id":"2208.02865","title":"Towards Augmented Microscopy with Reinforcement Learning-Enhanced Workflows","created":"2022-08-04","cited_by_count":2,"area":null},{"id":"2306.17766","title":"Comparing Reinforcement Learning and Human Learning using the Game of Hidden Rules","created":"2023-06-30","cited_by_count":2,"area":null},{"id":"2210.12599","title":"Transformers For Recognition In Overhead Imagery: A Reality Check","created":"2022-10-23","cited_by_count":1,"area":null},{"id":"2310.20380","title":"Dropout Strategy in Reinforcement Learning: Limiting the Surrogate Objective Variance in Policy Optimization Methods","created":"2023-10-31","cited_by_count":1,"area":null},{"id":"2311.05084","title":"Signal Temporal Logic-Guided Apprenticeship Learning","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2403.14425","title":"Task-optimal data-driven surrogate models for eNMPC via differentiable simulation and optimization","created":"2024-03-21","cited_by_count":1,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2101.09614","title":"A Methodology for the Development of RL-Based Adaptive Traffic Signal Controllers","created":"2021-01-24","cited_by_count":0,"area":null},{"id":"2103.04511","title":"An Energy-Saving Snake Locomotion Gait Policy Obtained Using Deep Reinforcement Learning","created":"2021-03-08","cited_by_count":0,"area":null},{"id":"2108.01215","title":"Variational Actor-Critic Algorithms","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2203.01075","title":"Reliable validation of Reinforcement Learning Benchmarks","created":"2022-03-02","cited_by_count":0,"area":null},{"id":"2209.09058","title":"Measuring Interventional Robustness in Reinforcement Learning","created":"2022-09-19","cited_by_count":0,"area":null},{"id":"2306.14606","title":"Multivariate Time Series Early Classification Across Channel and Time Dimensions","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2401.12295","title":"Cheap Learning: Maximising Performance of Language Models for Social Data Science Using Minimal Data","created":"2024-01-22","cited_by_count":0,"area":null},{"id":"2502.16446","title":"Auxiliary Discrminator Sequence Generative Adversarial Networks (ADSeqGAN) for Few Sample Molecule Generation","created":"2025-02-23","cited_by_count":0,"area":null},{"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}],"next_cursor":null}