{"list":"other","total":64,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"1807.00263","title":"Accurate Uncertainties for Deep Learning Using Calibrated Regression","created":"2018-07-01","cited_by_count":422},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","cited_by_count":366},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"1704.00445","title":"On Kernelized Multi-armed Bandits","created":"2017-04-03","cited_by_count":352},{"id":"1805.07708","title":"A Lyapunov-based Approach to Safe Reinforcement Learning","created":"2018-05-20","cited_by_count":297},{"id":"1801.08757","title":"Safe Exploration in Continuous Action Spaces","created":"2018-01-26","cited_by_count":247},{"id":"2010.15920","title":"Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones","created":"2020-10-29","cited_by_count":175},{"id":"1602.04450","title":"Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Robotics","created":"2016-02-14","cited_by_count":134},{"id":"2003.00534","title":"Provably Efficient Safe Exploration via Primal-Dual Policy Optimization","created":"2020-03-01","cited_by_count":134},{"id":"2011.05869","title":"CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee","created":"2020-11-11","cited_by_count":134},{"id":"1910.09615","title":"IPO: Interior-point Policy Optimization under Constraints","created":"2019-10-21","cited_by_count":132},{"id":"1803.08287","title":"Learning-based Model Predictive Control for Safe Exploration","created":"2018-03-22","cited_by_count":120},{"id":"1812.05506","title":"A predictive safety filter for learning-based control of constrained nonlinear dynamical systems","created":"2018-12-13","cited_by_count":118},{"id":"2010.14603","title":"Learning to be Safe: Deep RL with a Safety Critic","created":"2020-10-27","cited_by_count":116},{"id":"2008.06626","title":"Safe Reinforcement Learning in Constrained Markov Decision Processes","created":"2020-08-15","cited_by_count":115},{"id":"2010.14497","title":"Conservative Safety Critics for Exploration","created":"2020-10-27","cited_by_count":113},{"id":"2405.06624","title":"Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems","created":"2024-05-10","cited_by_count":96},{"id":"1705.10702","title":"Cautious Model Predictive Control using Gaussian Process Regression","created":"2017-05-30","cited_by_count":91},{"id":"1711.06782","title":"Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning","created":"2017-11-18","cited_by_count":90},{"id":"2006.12466","title":"Information Theoretic Regret Bounds for Online Nonlinear Control","created":"2020-06-22","cited_by_count":90},{"id":"2208.05767","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity","created":"2022-08-11","cited_by_count":87},{"id":"2006.08684","title":"Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning","created":"2020-06-15","cited_by_count":86},{"id":"2202.13890","title":"Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity","created":"2022-02-28","cited_by_count":85},{"id":"2003.11881","title":"An empirical investigation of the challenges of real-world reinforcement learning","created":"2020-03-24","cited_by_count":77},{"id":"1606.04753","title":"Safe Exploration in Finite Markov Decision Processes with Gaussian Processes","created":"2016-06-15","cited_by_count":75},{"id":"1902.03229","title":"Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces","created":"2019-02-08","cited_by_count":73},{"id":"2201.11927","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","created":"2022-01-28","cited_by_count":71},{"id":"2202.06558","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","created":"2022-02-14","cited_by_count":69},{"id":"2202.07789","title":"Safe Reinforcement Learning by Imagining the Near Future","created":"2022-02-15","cited_by_count":67},{"id":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59},{"id":"2201.09802","title":"Constrained Policy Optimization via Bayesian World Models","created":"2022-01-24","cited_by_count":57},{"id":"2307.07176","title":"SafeDreamer: Safe Reinforcement Learning with World Models","created":"2023-07-14","cited_by_count":54},{"id":"2106.09110","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","created":"2021-06-16","cited_by_count":47},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35},{"id":"2306.12371","title":"Optimistic Active Exploration of Dynamical Systems","created":"2023-06-21","cited_by_count":32},{"id":"1905.05150","title":"AMZ Driverless: The Full Autonomous Racing System","created":"2019-05-13","cited_by_count":29},{"id":"2310.03225","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","created":"2023-10-05","cited_by_count":28},{"id":"2305.16147","title":"Learning Safety Constraints from Demonstrations with Unknown Rewards","created":"2023-05-25","cited_by_count":19},{"id":"2201.09562","title":"GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems","created":"2022-01-24","cited_by_count":17},{"id":"2306.00629","title":"Identifiability and Generalizability in Constrained Inverse Reinforcement Learning","created":"2023-06-01","cited_by_count":16},{"id":"2107.04200","title":"Safe Exploration by Solving Early Terminated MDP","created":"2021-07-09","cited_by_count":15},{"id":"2406.15788","title":"Distributionally Robust Constrained Reinforcement Learning under Strong Duality","created":"2024-06-22","cited_by_count":15},{"id":"2301.12593","title":"Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning","created":"2023-01-30","cited_by_count":12},{"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},{"id":"2210.06380","title":"Near-Optimal Multi-Agent Learning for Safe Coverage Control","created":"2022-10-12","cited_by_count":11},{"id":"2312.00561","title":"A safe exploration approach to constrained Markov decision processes","created":"2023-12-01","cited_by_count":10},{"id":"2408.16286","title":"Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form","created":"2024-08-29","cited_by_count":10},{"id":"2402.06562","title":"Safe Guaranteed Exploration for Non-linear Systems","created":"2024-02-09","cited_by_count":8},{"id":"2207.01337","title":"Safe Reinforcement Learning via Confidence-Based Filters","created":"2022-07-04","cited_by_count":6},{"id":"2409.08616","title":"Towards safe and tractable Gaussian process-based MPC: Efficient sampling within a sequential quadratic programming framework","created":"2024-09-13","cited_by_count":6},{"id":"2505.07594","title":"Finite-Sample-Based Reachability for Safe Control with Gaussian Process Dynamics","created":"2025-05-12","cited_by_count":5},{"id":"2505.09349","title":"Safe Primal-Dual Optimization with a Single Smooth Constraint","created":"2025-05-14","cited_by_count":1}],"next_cursor":null}