{"total":59,"rows":[{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512,"area":"wm"},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407,"area":null},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203,"area":"alignment"},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"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":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59,"area":null},{"id":"2110.04135","title":"Revisiting Design Choices in Offline Model-Based Reinforcement Learning","created":"2021-10-08","cited_by_count":50,"area":"offlinerl"},{"id":"2203.09637","title":"Investigating Compounding Prediction Errors in Learned Dynamics Models","created":"2022-03-17","cited_by_count":47,"area":null},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46,"area":null},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42,"area":null},{"id":"2306.12370","title":"PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning","created":"2023-06-21","cited_by_count":31,"area":null},{"id":"2502.02133","title":"Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification","created":"2025-02-04","cited_by_count":26,"area":"deeprl"},{"id":"2207.09405","title":"Bayesian Generational Population-Based Training","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19,"area":null},{"id":"2303.02135","title":"Eventual Discounting Temporal Logic Counterfactual Experience Replay","created":"2023-03-03","cited_by_count":19,"area":null},{"id":"2303.02618","title":"Ensemble Reinforcement Learning: A Survey","created":"2023-03-05","cited_by_count":16,"area":null},{"id":"2303.08485","title":"Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML","created":"2023-03-15","cited_by_count":16,"area":null},{"id":"2403.10967","title":"Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization","created":"2024-03-16","cited_by_count":16,"area":"wm"},{"id":"2111.08550","title":"On Effective Scheduling of Model-based Reinforcement Learning","created":"2021-11-16","cited_by_count":13,"area":null},{"id":"2107.11587","title":"Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?","created":"2021-07-24","cited_by_count":11,"area":null},{"id":"2205.10629","title":"User-Interactive Offline Reinforcement Learning","created":"2022-05-21","cited_by_count":11,"area":"offlinerl"},{"id":"2306.11918","title":"Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback","created":"2023-06-20","cited_by_count":9,"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":"2110.07985","title":"On-Policy Model Errors in Reinforcement Learning","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2111.12673","title":"Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning","created":"2021-11-24","cited_by_count":6,"area":null},{"id":"2112.01853","title":"Episodic Policy Gradient Training","created":"2021-12-03","cited_by_count":5,"area":null},{"id":"2212.08235","title":"A Simple Decentralized Cross-Entropy Method","created":"2022-12-16","cited_by_count":5,"area":null},{"id":"2303.12803","title":"Evolving Populations of Diverse RL Agents with MAP-Elites","created":"2023-03-09","cited_by_count":5,"area":null},{"id":"2106.02229","title":"Differentiable Architecture Search for Reinforcement Learning","created":"2021-06-04","cited_by_count":4,"area":null},{"id":"2303.10144","title":"Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting","created":"2023-03-17","cited_by_count":4,"area":"wm"},{"id":"2306.01436","title":"Multi-Objective Population Based Training","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2310.18212","title":"Robustness of Algorithms for Causal Structure Learning to Hyperparameter Choice","created":"2023-10-27","cited_by_count":4,"area":null},{"id":"2205.10416","title":"ARLO: A Framework for Automated Reinforcement Learning","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2403.12210","title":"Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning","created":"2024-03-18","cited_by_count":3,"area":"deeprl"},{"id":"2409.18827","title":"ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning","created":"2024-09-27","cited_by_count":3,"area":"deeprl"},{"id":"2501.00989","title":"Bootstrapped Reward Shaping","created":"2025-01-02","cited_by_count":3,"area":"deeprl"},{"id":"2311.15854","title":"A systematic study comparing hyperparameter optimization engines on tabular data","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2403.01888","title":"Fast Benchmarking of Asynchronous Multi-Fidelity Optimization on Zero-Cost Benchmarks","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2203.01717","title":"Practitioner Motives to Use Different Hyperparameter Optimization Methods","created":"2022-03-03","cited_by_count":1,"area":null},{"id":"2204.04292","title":"Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability","created":"2022-04-08","cited_by_count":1,"area":null},{"id":"2209.11693","title":"T3VIP: Transformation-based 3D Video Prediction","created":"2022-09-19","cited_by_count":1,"area":null},{"id":"2304.14423","title":"Learning Environment for the Air Domain (LEAD)","created":"2023-04-27","cited_by_count":1,"area":null},{"id":"2402.02858","title":"Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning","created":"2024-02-05","cited_by_count":1,"area":"offlinerl"},{"id":"2403.04453","title":"Efficient Off-Policy Learning for High-Dimensional Action Spaces","created":"2024-03-07","cited_by_count":1,"area":"deeprl"},{"id":"2411.13211","title":"ViSTa Dataset: Do vision-language models understand sequential tasks?","created":"2024-11-20","cited_by_count":1,"area":"mllm"},{"id":"2503.06101","title":"ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning","created":"2025-03-08","cited_by_count":1,"area":"deeprl"},{"id":"2504.06683","title":"Hyperparameter Optimisation with Practical Interpretability and Explanation Methods in Probabilistic Curriculum Learning","created":"2025-04-09","cited_by_count":1,"area":"deeprl"},{"id":"2506.03225","title":"Multiple-Frequencies Population-Based Training","created":"2025-06-03","cited_by_count":1,"area":"deeprl"},{"id":"2112.08094","title":"Automatic tuning of hyper-parameters of reinforcement learning algorithms using Bayesian optimization with behavioral cloning","created":"2021-12-15","cited_by_count":0,"area":"offlinerl"},{"id":"2201.08987","title":"Survival Prediction of Children Undergoing Hematopoietic Stem Cell Transplantation Using Different Machine Learning Classifiers by Performing Chi-squared Test and Hyper-parameter Optimization: A Retrospective Analysis","created":"2022-01-22","cited_by_count":0,"area":null},{"id":"2202.00617","title":"A General, Evolution-Inspired Reward Function for Social Robotics","created":"2022-02-01","cited_by_count":0,"area":"offlinerl"},{"id":"2210.17491","title":"Learning Modular Robot Locomotion from Demonstrations","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2211.08536","title":"Behavior of Hyper-Parameters for Selected Machine Learning Algorithms: An Empirical Investigation","created":"2022-11-15","cited_by_count":0,"area":null},{"id":"2303.05186","title":"A Framework for History-Aware Hyperparameter Optimisation in Reinforcement Learning","created":"2023-03-09","cited_by_count":0,"area":null},{"id":"2409.14412","title":"COSBO: Conservative Offline Simulation-Based Policy Optimization","created":"2024-09-22","cited_by_count":0,"area":"offlinerl"},{"id":"2507.08053","title":"Tree-Structured Parzen Estimator Can Solve Black-Box Combinatorial Optimization More Efficiently","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2606.05555","title":"Representation Learning Enables Scalable Multitask Deep Reinforcement Learning","created":"2026-06-04","cited_by_count":0,"area":"deeprl"},{"id":"2607.26680","title":"Efficient Heteroscedastic Bayesian Optimization for Risk-Aware AutoRL","created":"2026-07-29","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}