{"list":"other","total":57,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"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":"2007.03964","title":"Responsive Safety in Reinforcement Learning by PID Lagrangian Methods","created":"2020-07-08","cited_by_count":316},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"1903.08792","title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","created":"2019-03-21","cited_by_count":289},{"id":"1609.06408","title":"Control Barrier Function Based Quadratic Programs for Safety Critical Systems","created":"2016-09-21","cited_by_count":287},{"id":"1801.08757","title":"Safe Exploration in Continuous Action Spaces","created":"2018-01-26","cited_by_count":247},{"id":"1903.08738","title":"Batch Policy Learning under Constraints","created":"2019-03-20","cited_by_count":244},{"id":"2010.03152","title":"Projection-Based Constrained Policy Optimization","created":"2020-10-07","cited_by_count":203},{"id":"2101.06286","title":"Reinforcement learning based recommender systems: A survey","created":"2021-01-15","cited_by_count":188},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"id":"2010.15920","title":"Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones","created":"2020-10-29","cited_by_count":175},{"id":"1705.01292","title":"A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems","created":"2017-05-03","cited_by_count":163},{"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":"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":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110},{"id":"2107.09003","title":"Constraints Penalized Q-learning for Safe Offline Reinforcement Learning","created":"2021-07-19","cited_by_count":91},{"id":"2305.09304","title":"OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research","created":"2023-05-16","cited_by_count":80},{"id":"1606.04753","title":"Safe Exploration in Finite Markov Decision Processes with Gaussian Processes","created":"2016-06-15","cited_by_count":75},{"id":"2006.12136","title":"Safe Reinforcement Learning via Curriculum Induction","created":"2020-06-22","cited_by_count":74},{"id":"2201.11927","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","created":"2022-01-28","cited_by_count":71},{"id":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71},{"id":"1709.07643","title":"OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real World","created":"2017-09-22","cited_by_count":70},{"id":"2202.06558","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","created":"2022-02-14","cited_by_count":69},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69},{"id":"2205.11814","title":"Penalized Proximal Policy Optimization for Safe Reinforcement Learning","created":"2022-05-24","cited_by_count":68},{"id":"2202.07789","title":"Safe Reinforcement Learning by Imagining the Near Future","created":"2022-02-15","cited_by_count":67},{"id":"2209.15090","title":"Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments","created":"2022-09-29","cited_by_count":60},{"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":"2302.03122","title":"State-wise Safe Reinforcement Learning: A Survey","created":"2023-02-06","cited_by_count":55},{"id":"2109.06332","title":"Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach","created":"2021-09-13","cited_by_count":50},{"id":"1910.10885","title":"Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics","created":"2019-10-24","cited_by_count":47},{"id":"2002.12156","title":"Cautious Reinforcement Learning with Logical Constraints","created":"2020-02-26","cited_by_count":45},{"id":"2106.06239","title":"Safe Reinforcement Learning with Linear Function Approximation","created":"2021-06-11","cited_by_count":35},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35},{"id":"2201.12427","title":"Towards Safe Reinforcement Learning with a Safety Editor Policy","created":"2022-01-28","cited_by_count":30},{"id":"2310.03225","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","created":"2023-10-05","cited_by_count":28},{"id":"2010.05150","title":"Safe Reinforcement Learning with Natural Language Constraints","created":"2020-10-11","cited_by_count":23},{"id":"2112.13941","title":"Safe Reinforcement Learning with Chance-constrained Model Predictive Control","created":"2021-12-27","cited_by_count":20},{"id":"1709.05077","title":"Transforming Cooling Optimization for Green Data Center via Deep Reinforcement Learning","created":"2017-09-15","cited_by_count":18},{"id":"2302.04375","title":"A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints","created":"2023-02-08","cited_by_count":17},{"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},{"id":"2104.11706","title":"Safe Chance Constrained Reinforcement Learning for Batch Process Control","created":"2021-04-23","cited_by_count":11},{"id":"2306.12594","title":"State-wise Constrained Policy Optimization","created":"2023-06-21","cited_by_count":9}],"next_cursor":null}