{"list":"other","total":56,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"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":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"1903.11199","title":"Control Barrier Functions: Theory and Applications","created":"2019-03-27","cited_by_count":372},{"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":"1805.07708","title":"A Lyapunov-based Approach to Safe Reinforcement Learning","created":"2018-05-20","cited_by_count":297},{"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":"1801.08757","title":"Safe Exploration in Continuous Action Spaces","created":"2018-01-26","cited_by_count":247},{"id":"2010.03152","title":"Projection-Based Constrained Policy Optimization","created":"2020-10-07","cited_by_count":203},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","cited_by_count":177},{"id":"2010.15920","title":"Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones","created":"2020-10-29","cited_by_count":175},{"id":"2006.14171","title":"A Closer Look at Invalid Action Masking in Policy Gradient Algorithms","created":"2020-06-25","cited_by_count":171},{"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":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"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":"1612.03471","title":"Reinforcement Learning With Temporal Logic Rewards","created":"2016-12-11","cited_by_count":117},{"id":"1906.04005","title":"Safe Reinforcement Learning Using Robust MPC","created":"2019-06-10","cited_by_count":85},{"id":"1709.06196","title":"Online algorithms for POMDPs with continuous state, action, and observation spaces","created":"2017-09-18","cited_by_count":84},{"id":"1909.05304","title":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees","created":"2019-09-11","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":"1810.00950","title":"Omega-Regular Objectives in Model-Free Reinforcement Learning","created":"2018-09-26","cited_by_count":75},{"id":"1807.06333","title":"Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specifications","created":"2018-07-17","cited_by_count":72},{"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":"1912.10099","title":"Learning for Safety-Critical Control with Control Barrier Functions","created":"2019-12-20","cited_by_count":69},{"id":"1609.07409","title":"Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications","created":"2016-09-23","cited_by_count":67},{"id":"2009.12612","title":"Neurosymbolic Reinforcement Learning with Formally Verified Exploration","created":"2020-09-26","cited_by_count":49},{"id":"2002.12156","title":"Cautious Reinforcement Learning with Logical Constraints","created":"2020-02-26","cited_by_count":45},{"id":"2102.12855","title":"Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic","created":"2021-02-24","cited_by_count":39},{"id":"2004.00915","title":"Safe Reinforcement Learning via Projection on a Safe Set: How to Achieve Optimality?","created":"2020-04-02","cited_by_count":34},{"id":"2007.01223","title":"Verifiably Safe Exploration for End-to-End Reinforcement Learning","created":"2020-07-02","cited_by_count":34},{"id":"2011.08421","title":"Reachability-based Trajectory Safeguard (RTS): A Safe and Fast Reinforcement Learning Safety Layer for Continuous Control","created":"2020-11-17","cited_by_count":28},{"id":"2003.06041","title":"On Robustness Metrics for Learning STL Tasks","created":"2020-03-12","cited_by_count":27},{"id":"2204.07417","title":"Safe Reinforcement Learning Using Black-Box Reachability Analysis","created":"2022-04-15","cited_by_count":26},{"id":"2110.10333","title":"Computationally Efficient Safe Reinforcement Learning for Power Systems","created":"2021-10-20","cited_by_count":20},{"id":"2111.12679","title":"On the (In)Tractability of Reinforcement Learning for LTL Objectives","created":"2021-11-24","cited_by_count":18},{"id":"2205.06311","title":"Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environments","created":"2022-05-12","cited_by_count":18},{"id":"1902.05632","title":"Verifiably Safe Off-Model Reinforcement Learning","created":"2019-02-14","cited_by_count":16},{"id":"1910.04803","title":"Autonomous Driving using Safe Reinforcement Learning by Incorporating a Regret-based Human Lane-Changing Decision Model","created":"2019-10-10","cited_by_count":14},{"id":"2101.05916","title":"Scalable Learning of Safety Guarantees for Autonomous Systems using Hamilton-Jacobi Reachability","created":"2021-01-15","cited_by_count":14},{"id":"2012.09539","title":"Online Shielding for Stochastic Systems","created":"2020-12-17","cited_by_count":11},{"id":"2105.14218","title":"A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehicles","created":"2021-05-29","cited_by_count":10},{"id":"2109.13446","title":"Runtime Safety Assurance for Learning-enabled Control of Autonomous Driving Vehicles","created":"2021-09-28","cited_by_count":9},{"id":"2205.06212","title":"Contingency-constrained economic dispatch with safe reinforcement learning","created":"2022-05-12","cited_by_count":8},{"id":"2003.08028","title":"A Control Barrier Perspective on Episodic Learning via Projection-to-State Safety","created":"2020-03-18","cited_by_count":7},{"id":"2112.10949","title":"District Cooling System Control for Providing Operating Reserve based on Safe Deep Reinforcement Learning","created":"2021-12-21","cited_by_count":6},{"id":"2111.15152","title":"SAVER: Safe Learning-Based Controller for Real-Time Voltage Regulation","created":"2021-11-30","cited_by_count":5},{"id":"1901.01006","title":"Invariant, Viability and Discriminating Kernel Under-Approximation via Zonotope Scaling","created":"2019-01-04","cited_by_count":3}],"next_cursor":null}