{"list":"other","total":50,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"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":"1612.03471","title":"Reinforcement Learning With Temporal Logic Rewards","created":"2016-12-11","cited_by_count":117},{"id":"1909.05304","title":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees","created":"2019-09-11","cited_by_count":77},{"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":"1609.07409","title":"Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications","created":"2016-09-23","cited_by_count":67},{"id":"1704.04341","title":"Environment-Independent Task Specifications via GLTL","created":"2017-04-14","cited_by_count":67},{"id":"2002.07080","title":"The Probabilistic Model Checker Storm","created":"2020-02-17","cited_by_count":66},{"id":"1404.7073","title":"Probably Approximately Correct MDP Learning and Control With Temporal Logic Constraints","created":"2014-04-28","cited_by_count":54},{"id":"1409.5486","title":"A Learning Based Approach to Control Synthesis of Markov Decision Processes for Linear Temporal Logic Specifications","created":"2014-09-18","cited_by_count":49},{"id":"2009.12612","title":"Neurosymbolic Reinforcement Learning with Formally Verified Exploration","created":"2020-09-26","cited_by_count":49},{"id":"1907.07273","title":"An Inductive Synthesis Framework for Verifiable Reinforcement Learning","created":"2019-07-16","cited_by_count":39},{"id":"2309.13528","title":"Iterative Reachability Estimation for Safe Reinforcement Learning","created":"2023-09-24","cited_by_count":37},{"id":"2007.01223","title":"Verifiably Safe Exploration for End-to-End Reinforcement Learning","created":"2020-07-02","cited_by_count":34},{"id":"1510.05880","title":"Safety-Constrained Reinforcement Learning for MDPs","created":"2015-10-20","cited_by_count":33},{"id":"2301.09937","title":"Explainable Deep Reinforcement Learning: State of the Art and Challenges","created":"2023-01-24","cited_by_count":33},{"id":"1811.02052","title":"Managing engineering systems with large state and action spaces through deep reinforcement learning","created":"2018-11-05","cited_by_count":32},{"id":"2001.09467","title":"Tractable Reinforcement Learning of Signal Temporal Logic Objectives","created":"2020-01-26","cited_by_count":22},{"id":"2010.06797","title":"Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction","created":"2020-10-14","cited_by_count":22},{"id":"2209.07133","title":"COOL-MC: A Comprehensive Tool for Reinforcement Learning and Model Checking","created":"2022-09-15","cited_by_count":19},{"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":"1504.04662","title":"Permissive Controller Synthesis for Probabilistic Systems","created":"2015-04-18","cited_by_count":17},{"id":"2005.07073","title":"Probabilistic Guarantees for Safe Deep Reinforcement Learning","created":"2020-05-14","cited_by_count":15},{"id":"2305.17115","title":"Policy Synthesis and Reinforcement Learning for Discounted LTL","created":"2023-05-26","cited_by_count":14},{"id":"2410.12175","title":"Reinforcement Learning with LTL and $\\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards","created":"2024-10-16","cited_by_count":14},{"id":"2009.04547","title":"Optimal Inspection and Maintenance Planning for Deteriorating Structural Components through Dynamic Bayesian Networks and Markov Decision Processes","created":"2020-09-09","cited_by_count":13},{"id":"2307.08082","title":"POMDP inference and robust solution via deep reinforcement learning: An application to railway optimal maintenance","created":"2023-07-16","cited_by_count":13},{"id":"2209.01092","title":"Inference and dynamic decision-making for deteriorating systems with probabilistic dependencies through Bayesian networks and deep reinforcement learning","created":"2022-09-02","cited_by_count":11},{"id":"2308.02594","title":"SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents","created":"2023-08-03","cited_by_count":10},{"id":"2110.03184","title":"Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Model","created":"2021-10-07","cited_by_count":9},{"id":"2409.10218","title":"Safety-Oriented Pruning and Interpretation of Reinforcement Learning Policies","created":"2024-09-16","cited_by_count":9},{"id":"2010.10618","title":"Runtime Safety Assurance Using Reinforcement Learning","created":"2020-10-20","cited_by_count":8},{"id":"2404.18326","title":"SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies","created":"2024-04-28","cited_by_count":8},{"id":"2405.15994","title":"Verified Safe Reinforcement Learning for Neural Network Dynamic Models","created":"2024-05-25","cited_by_count":7},{"id":"2201.03698","title":"Verified Probabilistic Policies for Deep Reinforcement Learning","created":"2022-01-10","cited_by_count":6},{"id":"2409.10188","title":"Enhancing RL Safety with Counterfactual LLM Reasoning","created":"2024-09-16","cited_by_count":6},{"id":"2411.07591","title":"Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization","created":"2024-11-12","cited_by_count":6},{"id":"2212.05337","title":"Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking","created":"2022-12-10","cited_by_count":5},{"id":"2401.12455","title":"Multi-agent deep reinforcement learning with centralized training and decentralized execution for transportation infrastructure management","created":"2024-01-23","cited_by_count":5},{"id":"2001.05977","title":"Reward Shaping for Reinforcement Learning with Omega-Regular Objectives","created":"2020-01-16","cited_by_count":4},{"id":"2106.06931","title":"Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learning","created":"2021-06-13","cited_by_count":3},{"id":"2109.06523","title":"Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking","created":"2021-09-14","cited_by_count":3},{"id":"2112.12589","title":"A deep reinforcement learning model for predictive maintenance planning of road assets: Integrating LCA and LCCA","created":"2021-12-20","cited_by_count":3},{"id":"2501.03187","title":"Turn-based Multi-Agent Reinforcement Learning Model Checking","created":"2025-01-06","cited_by_count":3},{"id":"2602.14505","title":"Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC","created":"2026-02-16","cited_by_count":3},{"id":"2311.09811","title":"Runtime Verification of Learning Properties for Reinforcement Learning Algorithms","created":"2023-11-16","cited_by_count":2},{"id":"2501.03142","title":"Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies","created":"2025-01-06","cited_by_count":2},{"id":"2107.03685","title":"Towards Autonomous Pipeline Inspection with Hierarchical Reinforcement Learning","created":"2021-07-08","cited_by_count":1},{"id":"2406.06184","title":"Deep Multi-Objective Reinforcement Learning for Utility-Based Infrastructural Maintenance Optimization","created":"2024-06-10","cited_by_count":1}],"next_cursor":null}