{"total":134,"rows":[{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371,"area":null},{"id":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","cited_by_count":81,"area":null},{"id":"2206.04771","title":"Joint Entropy Search for Maximally-Informed Bayesian Optimization","created":"2022-06-09","cited_by_count":55,"area":null},{"id":"2108.09262","title":"Optimal Order Simple Regret for Gaussian Process Bandits","created":"2021-08-20","cited_by_count":54,"area":null},{"id":"2210.02905","title":"Joint Entropy Search for Multi-objective Bayesian Optimization","created":"2022-10-06","cited_by_count":45,"area":null},{"id":"2107.03144","title":"Neural Contextual Bandits without Regret","created":"2021-07-07","cited_by_count":40,"area":null},{"id":"2110.14188","title":"RoMA: Robust Model Adaptation for Offline Model-based Optimization","created":"2021-10-27","cited_by_count":39,"area":null},{"id":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"area":"deeprl"},{"id":"2105.13281","title":"GoSafe: Globally Optimal Safe Robot Learning","created":"2021-05-27","cited_by_count":27,"area":null},{"id":"2302.05927","title":"Transfer Learning for Bayesian Optimization: A Survey","created":"2023-02-12","cited_by_count":27,"area":null},{"id":"2105.14937","title":"Safe Pontryagin Differentiable Programming","created":"2021-05-31","cited_by_count":26,"area":null},{"id":"2203.15589","title":"On Kernelized Multi-Armed Bandits with Constraints","created":"2022-03-29","cited_by_count":23,"area":null},{"id":"2410.09486","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","created":"2024-10-12","cited_by_count":23,"area":"deeprl"},{"id":"2304.11005","title":"Self-Correcting Bayesian Optimization through Bayesian Active Learning","created":"2023-04-21","cited_by_count":22,"area":null},{"id":"2111.03637","title":"Risk-averse Heteroscedastic Bayesian Optimization","created":"2021-11-05","cited_by_count":17,"area":null},{"id":"2201.09562","title":"GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems","created":"2022-01-24","cited_by_count":17,"area":null},{"id":"2303.01560","title":"Active Learning and Bayesian Optimization: a Unified Perspective to Learn with a Goal","created":"2023-03-02","cited_by_count":17,"area":null},{"id":"2101.09505","title":"Safe Learning and Optimization Techniques: Towards a Survey of the State of the Art","created":"2021-01-23","cited_by_count":16,"area":null},{"id":"2401.16373","title":"Bayesian optimization as a flexible and efficient design framework for sustainable process systems","created":"2024-01-29","cited_by_count":15,"area":null},{"id":"2403.12948","title":"On Safety in Safe Bayesian Optimization","created":"2024-03-19","cited_by_count":15,"area":null},{"id":"2404.09080","title":"Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications","created":"2024-04-13","cited_by_count":15,"area":"deeprl"},{"id":"2502.06363","title":"Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance","created":"2025-02-10","cited_by_count":15,"area":null},{"id":"2210.00762","title":"Meta-Learning Priors for Safe Bayesian Optimization","created":"2022-10-03","cited_by_count":14,"area":null},{"id":"2203.14849","title":"Safe Active Learning for Multi-Output Gaussian Processes","created":"2022-03-28","cited_by_count":13,"area":null},{"id":"2205.13170","title":"Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost","created":"2022-05-26","cited_by_count":13,"area":null},{"id":"2207.11120","title":"On Controller Tuning with Time-Varying Bayesian Optimization","created":"2022-07-22","cited_by_count":13,"area":null},{"id":"2103.11489","title":"UCB-based Algorithms for Multinomial Logistic Regression Bandits","created":"2021-03-21","cited_by_count":12,"area":null},{"id":"2109.09264","title":"Computationally Efficient High-Dimensional Bayesian Optimization via Variable Selection","created":"2021-09-20","cited_by_count":12,"area":null},{"id":"2312.10199","title":"Automatic nonlinear MPC approximation with closed-loop guarantees","created":"2023-12-15","cited_by_count":12,"area":null},{"id":"2207.10415","title":"Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning","created":"2022-07-21","cited_by_count":11,"area":null},{"id":"2101.07825","title":"Safe and Efficient Model-free Adaptive Control via Bayesian Optimization","created":"2021-01-19","cited_by_count":10,"area":null},{"id":"2201.13248","title":"SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation","created":"2022-01-27","cited_by_count":10,"area":null},{"id":"2212.01574","title":"Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUS","created":"2022-12-03","cited_by_count":10,"area":null},{"id":"2306.17815","title":"Bayesian Optimization with Formal Safety Guarantees via Online Conformal Prediction","created":"2023-06-30","cited_by_count":10,"area":null},{"id":"2312.00561","title":"A safe exploration approach to constrained Markov decision processes","created":"2023-12-01","cited_by_count":10,"area":null},{"id":"2503.10352","title":"Safe exploration in reproducing kernel Hilbert spaces","created":"2025-03-13","cited_by_count":10,"area":null},{"id":"2105.13245","title":"Bayesian Optimisation for Constrained Problems","created":"2021-05-27","cited_by_count":9,"area":null},{"id":"2211.14720","title":"Rectified Pessimistic-Optimistic Learning for Stochastic Continuum-armed Bandit with Constraints","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2212.04914","title":"Information-Theoretic Safe Exploration with Gaussian Processes","created":"2022-12-09","cited_by_count":9,"area":null},{"id":"2306.07092","title":"Tuning Legged Locomotion Controllers via Safe Bayesian Optimization","created":"2023-06-12","cited_by_count":9,"area":null},{"id":"2402.06562","title":"Safe Guaranteed Exploration for Non-linear Systems","created":"2024-02-09","cited_by_count":8,"area":null},{"id":"2409.01163","title":"PACSBO: Probably approximately correct safe Bayesian optimization","created":"2024-09-02","cited_by_count":8,"area":null},{"id":"2101.05328","title":"Uniform Error and Posterior Variance Bounds for Gaussian Process Regression with Application to Safe Control","created":"2021-01-13","cited_by_count":7,"area":null},{"id":"2203.13968","title":"Tuning Particle Accelerators with Safety Constraints using Bayesian Optimization","created":"2022-03-26","cited_by_count":7,"area":null},{"id":"2207.06196","title":"Interactive Machine Learning: A State of the Art Review","created":"2022-07-13","cited_by_count":6,"area":null},{"id":"2305.03824","title":"No-Regret Constrained Bayesian Optimization of Noisy and Expensive Hybrid Models using Differentiable Quantile Function Approximations","created":"2023-05-05","cited_by_count":6,"area":null},{"id":"2305.20011","title":"Constrained Causal Bayesian Optimization","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2310.20145","title":"Efficient Robust Bayesian Optimization for Arbitrary Uncertain Inputs","created":"2023-10-31","cited_by_count":6,"area":null},{"id":"2402.07692","title":"Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints","created":"2024-02-12","cited_by_count":6,"area":null},{"id":"2503.07127","title":"Performance-driven Constrained Optimal Auto-Tuner for MPC","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2510.05516","title":"NeST-BO: Fast Local Bayesian Optimization via Newton-Step Targeting of Gradient and Hessian Information","created":"2025-10-07","cited_by_count":6,"area":null},{"id":"2601.19612","title":"Safe Exploration via Policy Priors","created":"2026-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2603.02196","title":"Conformal Policy Control","created":"2026-03-02","cited_by_count":6,"area":null},{"id":"2102.10806","title":"Provably Correct Training of Neural Network Controllers Using Reachability Analysis","created":"2021-02-22","cited_by_count":5,"area":null},{"id":"2103.14452","title":"Robot Program Parameter Inference via Differentiable Shadow Program Inversion","created":"2021-03-26","cited_by_count":5,"area":null},{"id":"2111.05589","title":"Safe Real-Time Optimization using Multi-Fidelity Gaussian Processes","created":"2021-11-10","cited_by_count":5,"area":null},{"id":"2203.02570","title":"Bayesian Optimization Meets Hybrid Zero Dynamics: Safe Parameter Learning for Bipedal Locomotion Control","created":"2022-03-04","cited_by_count":5,"area":null},{"id":"2205.09548","title":"ODBO: Bayesian Optimization with Search Space Prescreening for Directed Protein Evolution","created":"2022-05-19","cited_by_count":5,"area":null},{"id":"2211.00077","title":"Optimizing Closed-Loop Performance with Data from Similar Systems: A Bayesian Meta-Learning Approach","created":"2022-10-31","cited_by_count":5,"area":null},{"id":"2211.02045","title":"Fast and robust Bayesian Inference using Gaussian Processes with GPry","created":"2022-11-03","cited_by_count":5,"area":null},{"id":"2310.03515","title":"High-dimensional Bayesian Optimization with Group Testing","created":"2023-10-05","cited_by_count":5,"area":null},{"id":"2312.07281","title":"Towards Safe Multi-Task Bayesian Optimization","created":"2023-12-12","cited_by_count":5,"area":null},{"id":"2507.00480","title":"Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization","created":"2025-07-01","cited_by_count":5,"area":null},{"id":"2207.07524","title":"Heuristic-free Optimization of Force-Controlled Robot Search Strategies in Stochastic Environments","created":"2022-07-15","cited_by_count":4,"area":null},{"id":"2212.14118","title":"Falsification of Learning-Based Controllers through Multi-Fidelity Bayesian Optimization","created":"2022-12-28","cited_by_count":4,"area":null},{"id":"2405.05890","title":"Safe Exploration Using Bayesian World Models and Log-Barrier Optimization","created":"2024-05-09","cited_by_count":4,"area":"wm"},{"id":"2405.19059","title":"Robust Entropy Search for Safe Efficient Bayesian Optimization","created":"2024-05-29","cited_by_count":4,"area":null},{"id":"2409.18000","title":"Safe Time-Varying Optimization based on Gaussian Processes with Spatio-Temporal Kernel","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2412.20350","title":"Safe Bayesian Optimization for the Control of High-Dimensional Embodied Systems","created":"2024-12-29","cited_by_count":4,"area":null},{"id":"2505.22235","title":"Optimal kernel regression bounds under energy-bounded noise","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2507.09828","title":"Regret Analysis of Posterior Sampling-Based Expected Improvement for Bayesian Optimization","created":"2025-07-13","cited_by_count":4,"area":null},{"id":"2204.09833","title":"Sample-Based Bounds for Coherent Risk Measures: Applications to Policy Synthesis and Verification","created":"2022-04-21","cited_by_count":3,"area":null},{"id":"2304.06104","title":"Primal-Dual Contextual Bayesian Optimization for Control System Online Optimization with Time-Average Constraints","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2305.00889","title":"The Impact of the Geometric Properties of the Constraint Set in Safe Optimization with Bandit Feedback","created":"2023-05-01","cited_by_count":3,"area":null},{"id":"2309.03672","title":"A computationally lightweight safe learning algorithm","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2311.09591","title":"Accelerating material discovery with a threshold-driven hybrid acquisition policy-based Bayesian optimization","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2411.16267","title":"Local Bayesian Optimization for Controller Tuning with Crash Constraints","created":"2024-11-25","cited_by_count":3,"area":null},{"id":"2501.15458","title":"Amortized Safe Active Learning for Real-Time Data Acquisition: Pretrained Neural Policies From Simulated Nonparametric Functions","created":"2025-01-26","cited_by_count":3,"area":null},{"id":"2201.01323","title":"Test and Evaluation of Quadrupedal Walking Gaits through Sim2Real Gap Quantification","created":"2022-01-04","cited_by_count":2,"area":null},{"id":"2209.06735","title":"Falsification of Cyber-Physical Systems using Bayesian Optimization","created":"2022-09-14","cited_by_count":2,"area":null},{"id":"2402.05399","title":"CURE: Simulation-Augmented Auto-Tuning in Robotics","created":"2024-02-08","cited_by_count":2,"area":null},{"id":"2407.15660","title":"MuTT: A Multimodal Trajectory Transformer for Robot Skills","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2410.15543","title":"Distributed Thompson sampling under constrained communication","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2503.01126","title":"Constrained multi-fidelity Bayesian optimization with automatic stop condition","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2504.06111","title":"Leveraging Axis-Aligned Subspaces for High-Dimensional Bayesian Optimization with Group Testing","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2505.08026","title":"Safety and optimality in learning-based control at low computational cost","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2505.12471","title":"Wasserstein Barycenter Gaussian Process based Bayesian Optimization","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2505.22861","title":"Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2510.00373","title":"Combining Large Language Models and Gradient-Free Optimization for Automatic Control Policy Synthesis","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2601.05152","title":"Safe Continual Reinforcement Learning Methods for Nonstationary Environments. Towards a Survey of the State of the Art","created":"2026-01-08","cited_by_count":2,"area":"deeprl"},{"id":"2603.01470","title":"Randomized Kriging Believer for Parallel Bayesian Optimization with Regret Bounds","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2605.26990","title":"Constrained Bayesian Experimental Design via Online Planning","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2207.09298","title":"Magpie: Automatically Tuning Static Parameters for Distributed File Systems using Deep Reinforcement Learning","created":"2022-07-19","cited_by_count":1,"area":null},{"id":"2211.01561","title":"Benefits of Monotonicity in Safe Exploration with Gaussian Processes","created":"2022-11-03","cited_by_count":1,"area":null},{"id":"2307.08024","title":"Bayesian inference for data-efficient, explainable, and safe robotic motion planning: A review","created":"2023-07-16","cited_by_count":1,"area":null},{"id":"2312.09961","title":"Risk-Aware Continuous Control with Neural Contextual Bandits","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2401.05876","title":"Safe reinforcement learning in uncertain contexts","created":"2024-01-11","cited_by_count":1,"area":"deeprl"},{"id":"2402.14402","title":"Global Safe Sequential Learning via Efficient Knowledge Transfer","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2405.10581","title":"Future Aware Safe Active Learning of Time Varying Systems using Gaussian Processes","created":"2024-05-17","cited_by_count":1,"area":null}],"next_cursor":"100"}