{"list":"other","total":60,"rows":[{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"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":"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":"1609.06408","title":"Control Barrier Function Based Quadratic Programs for Safety Critical Systems","created":"2016-09-21","cited_by_count":287},{"id":"2102.12086","title":"Modern Koopman Theory for Dynamical Systems","created":"2021-02-24","cited_by_count":276},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"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":"1901.10031","title":"Lyapunov-based Safe Policy Optimization for Continuous Control","created":"2019-01-28","cited_by_count":145},{"id":"2310.12567","title":"Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark","created":"2023-10-19","cited_by_count":143},{"id":"1711.09883","title":"AI Safety Gridworlds","created":"2017-11-27","cited_by_count":110},{"id":"1906.04005","title":"Safe Reinforcement Learning Using Robust MPC","created":"2019-06-10","cited_by_count":85},{"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":"2101.11196","title":"Safe Multi-Agent Reinforcement Learning via Shielding","created":"2021-01-27","cited_by_count":61},{"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":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50},{"id":"2109.06325","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","created":"2021-09-13","cited_by_count":50},{"id":"2108.11510","title":"Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey","created":"2021-08-25","cited_by_count":43},{"id":"1810.11748","title":"DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback","created":"2018-10-28","cited_by_count":41},{"id":"2302.08242","title":"Tuning computer vision models with task rewards","created":"2023-02-16","cited_by_count":37},{"id":"2107.04989","title":"Stabilizing Neural Control Using Self-Learned Almost Lyapunov Critics","created":"2021-07-11","cited_by_count":35},{"id":"2406.05309","title":"CoBL-Diffusion: Diffusion-Based Conditional Robot Planning in Dynamic Environments Using Control Barrier and Lyapunov Functions","created":"2024-06-08","cited_by_count":33},{"id":"2103.01556","title":"Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function","created":"2021-03-02","cited_by_count":32},{"id":"2207.06572","title":"i-Sim2Real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loops","created":"2022-07-14","cited_by_count":32},{"id":"2208.06721","title":"Lyapunov Design for Robust and Efficient Robotic Reinforcement Learning","created":"2022-08-13","cited_by_count":28},{"id":"1903.09885","title":"Temporal Logic Guided Safe Reinforcement Learning Using Control Barrier Functions","created":"2019-03-23","cited_by_count":21},{"id":"2107.00783","title":"Reinforcement Learning for Feedback-Enabled Cyber Resilience","created":"2021-07-02","cited_by_count":19},{"id":"1801.09627","title":"Barrier-Certified Adaptive Reinforcement Learning with Applications to Brushbot Navigation","created":"2018-01-29","cited_by_count":18},{"id":"2204.03516","title":"Distributed Reinforcement Learning for Robot Teams: A Review","created":"2022-04-07","cited_by_count":16},{"id":"2002.10126","title":"Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach","created":"2020-02-24","cited_by_count":13},{"id":"2204.04905","title":"Evaluating Vision Transformer Methods for Deep Reinforcement Learning from Pixels","created":"2022-04-11","cited_by_count":13},{"id":"2304.04066","title":"Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach","created":"2023-04-08","cited_by_count":13},{"id":"2305.09793","title":"Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions","created":"2023-05-16","cited_by_count":13},{"id":"2104.08171","title":"Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functions","created":"2021-04-16","cited_by_count":11},{"id":"2211.17250","title":"Safe and Efficient Reinforcement Learning Using Disturbance-Observer-Based Control Barrier Functions","created":"2022-11-30","cited_by_count":11},{"id":"2403.01410","title":"Barrier Functions Inspired Reward Shaping for Reinforcement Learning","created":"2024-03-03","cited_by_count":11},{"id":"2103.12553","title":"Safe Multi-Agent Reinforcement Learning through Decentralized Multiple Control Barrier Functions","created":"2021-03-23","cited_by_count":10},{"id":"2103.14186","title":"Barrier Function-based Safe Reinforcement Learning for Emergency Control of Power Systems","created":"2021-03-26","cited_by_count":8},{"id":"2403.08448","title":"Actor-Critic Physics-informed Neural Lyapunov Control","created":"2024-03-13","cited_by_count":8},{"id":"2304.03326","title":"Finite Time Lyapunov Exponent Analysis of Model Predictive Control and Reinforcement Learning","created":"2023-04-06","cited_by_count":7},{"id":"2207.01337","title":"Safe Reinforcement Learning via Confidence-Based Filters","created":"2022-07-04","cited_by_count":6},{"id":"2004.10331","title":"Learning Min-norm Stabilizing Control Laws for Systems with Unknown Dynamics","created":"2020-04-21","cited_by_count":5},{"id":"2211.05500","title":"Reinforcement Learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts","created":"2022-11-10","cited_by_count":4},{"id":"2107.13944","title":"Lyapunov-based uncertainty-aware safe reinforcement learning","created":"2021-07-29","cited_by_count":3},{"id":"2208.02029","title":"Supervised and Reinforcement Learning from Observations in Reconnaissance Blind Chess","created":"2022-08-03","cited_by_count":3},{"id":"2401.05525","title":"Towards Safe Load Balancing based on Control Barrier Functions and Deep Reinforcement Learning","created":"2024-01-10","cited_by_count":3},{"id":"2403.12210","title":"Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning","created":"2024-03-18","cited_by_count":3},{"id":"2405.08756","title":"Stable Inverse Reinforcement Learning: Policies from Control Lyapunov Landscapes","created":"2024-05-14","cited_by_count":3},{"id":"2205.08856","title":"Bridging the gap between QP-based and MPC-based RL","created":"2022-05-18","cited_by_count":1},{"id":"2206.07915","title":"Barrier Certified Safety Learning Control: When Sum-of-Square Programming Meets Reinforcement Learning","created":"2022-06-16","cited_by_count":1},{"id":"2503.15629","title":"Neural Lyapunov Function Approximation with Self-Supervised Reinforcement Learning","created":"2025-03-19","cited_by_count":1},{"id":"2505.10947","title":"Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions","created":"2025-05-16","cited_by_count":1}],"next_cursor":null}