{"list":"other","total":70,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"1901.08652","title":"Learning agile and dynamic motor skills for legged robots","created":"2019-01-24","cited_by_count":504},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"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":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"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":"1910.00935","title":"DiffTaichi: Differentiable Programming for Physical Simulation","created":"2019-10-01","cited_by_count":258},{"id":"2010.03950","title":"Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning","created":"2020-10-06","cited_by_count":191},{"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":"2202.11762","title":"Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methods","created":"2022-02-23","cited_by_count":151},{"id":"1703.08862","title":"Socially Aware Motion Planning with Deep Reinforcement Learning","created":"2017-03-26","cited_by_count":136},{"id":"2003.00534","title":"Provably Efficient Safe Exploration via Primal-Dual Policy Optimization","created":"2020-03-01","cited_by_count":134},{"id":"1612.03471","title":"Reinforcement Learning With Temporal Logic Rewards","created":"2016-12-11","cited_by_count":117},{"id":"2001.11231","title":"Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles","created":"2020-01-30","cited_by_count":110},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104},{"id":"2104.03311","title":"PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics","created":"2021-04-07","cited_by_count":103},{"id":"1810.01054","title":"ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics","created":"2018-10-02","cited_by_count":98},{"id":"2202.00817","title":"Do Differentiable Simulators Give Better Policy Gradients?","created":"2022-02-02","cited_by_count":89},{"id":"2111.05803","title":"Gradients are Not All You Need","created":"2021-11-10","cited_by_count":86},{"id":"1906.04005","title":"Safe Reinforcement Learning Using Robust MPC","created":"2019-06-10","cited_by_count":85},{"id":"1911.09101","title":"Safe Policies for Reinforcement Learning via Primal-Dual Methods","created":"2019-11-20","cited_by_count":79},{"id":"1909.05304","title":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees","created":"2019-09-11","cited_by_count":77},{"id":"1810.00950","title":"Omega-Regular Objectives in Model-Free Reinforcement Learning","created":"2018-09-26","cited_by_count":75},{"id":"1909.07299","title":"Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning","created":"2019-09-16","cited_by_count":75},{"id":"2101.05436","title":"Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates","created":"2021-01-14","cited_by_count":74},{"id":"1810.08700","title":"Safe Reinforcement Learning with Model Uncertainty Estimates","created":"2018-10-19","cited_by_count":72},{"id":"2004.07584","title":"Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions","created":"2020-04-16","cited_by_count":68},{"id":"1609.07409","title":"Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications","created":"2016-09-23","cited_by_count":67},{"id":"2105.12244","title":"DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting","created":"2021-05-25","cited_by_count":64},{"id":"2101.05917","title":"DiffPD: Differentiable Projective Dynamics","created":"2021-01-15","cited_by_count":62},{"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":"2205.07536","title":"Reachability Constrained Reinforcement Learning","created":"2022-05-16","cited_by_count":59},{"id":"1810.10408","title":"Multi-Agent Reinforcement Learning Based Resource Allocation for UAV Networks","created":"2018-10-24","cited_by_count":56},{"id":"1902.01240","title":"PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos","created":"2019-02-04","cited_by_count":56},{"id":"1404.7073","title":"Probably Approximately Correct MDP Learning and Control With Temporal Logic Constraints","created":"2014-04-28","cited_by_count":54},{"id":"2008.00097","title":"Backpropagation through Signal Temporal Logic Specifications: Infusing Logical Structure into Gradient-Based Methods","created":"2020-07-31","cited_by_count":54},{"id":"2107.07501","title":"An End-to-End Differentiable Framework for Contact-Aware Robot Design","created":"2021-07-15","cited_by_count":54},{"id":"2103.16021","title":"Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contact","created":"2021-03-30","cited_by_count":52},{"id":"2112.12288","title":"Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning","created":"2021-12-23","cited_by_count":49},{"id":"1910.10885","title":"Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics","created":"2019-10-24","cited_by_count":47},{"id":"1402.2967","title":"Verification of Markov Decision Processes using Learning Algorithms","created":"2014-02-10","cited_by_count":39},{"id":"2102.12855","title":"Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic","created":"2021-02-24","cited_by_count":39},{"id":"2109.07719","title":"Efficient Differentiable Simulation of Articulated Bodies","created":"2021-09-16","cited_by_count":39},{"id":"1902.00778","title":"Certified Reinforcement Learning with Logic Guidance","created":"2019-02-02","cited_by_count":36},{"id":"2003.04950","title":"Synthesis of Control Barrier Functions Using a Supervised Machine Learning Approach","created":"2020-03-10","cited_by_count":35},{"id":"2010.06797","title":"Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction","created":"2020-10-14","cited_by_count":22},{"id":"2405.17784","title":"Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation","created":"2024-05-28","cited_by_count":20},{"id":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19},{"id":"2303.02135","title":"Eventual Discounting Temporal Logic Counterfactual Experience Replay","created":"2023-03-03","cited_by_count":19},{"id":"2111.12679","title":"On the (In)Tractability of Reinforcement Learning for LTL Objectives","created":"2021-11-24","cited_by_count":18},{"id":"2305.01381","title":"Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees","created":"2023-05-02","cited_by_count":18},{"id":"2309.05131","title":"Signal Temporal Logic Neural Predictive Control","created":"2023-09-10","cited_by_count":13},{"id":"2310.12248","title":"A PAC Learning Algorithm for LTL and Omega-regular Objectives in MDPs","created":"2023-10-18","cited_by_count":13},{"id":"2201.12231","title":"Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments from Temporal Logic Specifications","created":"2022-01-28","cited_by_count":12},{"id":"2204.11833","title":"Joint Learning of Reward Machines and Policies in Environments with Partially Known Semantics","created":"2022-04-20","cited_by_count":12},{"id":"2205.04424","title":"Accelerated Reinforcement Learning for Temporal Logic Control Objectives","created":"2022-05-09","cited_by_count":9},{"id":"2311.02227","title":"State-Wise Safe Reinforcement Learning With Pixel Observations","created":"2023-11-03","cited_by_count":9},{"id":"2312.08710","title":"Gradient Informed Proximal Policy Optimization","created":"2023-12-14","cited_by_count":8},{"id":"2010.01050","title":"Model-Free Reinforcement Learning for Stochastic Games with Linear Temporal Logic Objectives","created":"2020-10-02","cited_by_count":7},{"id":"2103.14600","title":"Model-Free Learning of Safe yet Effective Controllers","created":"2021-03-26","cited_by_count":5},{"id":"2404.05074","title":"On the Uniqueness of Solution for the Bellman Equation of LTL Objectives","created":"2024-04-07","cited_by_count":3},{"id":"2011.01882","title":"Secure Planning Against Stealthy Attacks via Model-Free Reinforcement Learning","created":"2020-11-03","cited_by_count":2}],"next_cursor":null}