{"list":"other","total":95,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"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":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"1903.11199","title":"Control Barrier Functions: Theory and Applications","created":"2019-03-27","cited_by_count":372},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290},{"id":"1807.00412","title":"Learning to Drive in a Day","created":"2018-07-01","cited_by_count":273},{"id":"2309.16292","title":"DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models","created":"2023-09-28","cited_by_count":207},{"id":"2010.03950","title":"Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning","created":"2020-10-06","cited_by_count":191},{"id":"2007.04938","title":"SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","created":"2020-07-09","cited_by_count":152},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144},{"id":"2212.11419","title":"Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios","created":"2022-12-21","cited_by_count":129},{"id":"2003.06404","title":"A Survey of End-to-End Driving: Architectures and Training Methods","created":"2020-03-13","cited_by_count":123},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116},{"id":"2303.09824","title":"Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives","created":"2023-03-17","cited_by_count":114},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112},{"id":"2301.08028","title":"A Tutorial on Meta-Reinforcement Learning","created":"2023-01-19","cited_by_count":108},{"id":"2307.11046","title":"A Definition of Continual Reinforcement Learning","created":"2023-07-20","cited_by_count":101},{"id":"1904.09503","title":"Model-free Deep Reinforcement Learning for Urban Autonomous Driving","created":"2019-04-20","cited_by_count":98},{"id":"2309.05837","title":"The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systems","created":"2023-09-11","cited_by_count":88},{"id":"2001.02811","title":"Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors","created":"2020-01-09","cited_by_count":85},{"id":"2502.13144","title":"RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning","created":"2025-02-18","cited_by_count":79},{"id":"1802.05313","title":"Reinforcement Learning from Imperfect Demonstrations","created":"2018-02-14","cited_by_count":75},{"id":"2303.17220","title":"Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys","created":"2023-03-30","cited_by_count":75},{"id":"1810.08700","title":"Safe Reinforcement Learning with Model Uncertainty Estimates","created":"2018-10-19","cited_by_count":72},{"id":"2110.15360","title":"Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives","created":"2021-10-28","cited_by_count":65},{"id":"1902.00089","title":"Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving","created":"2019-01-29","cited_by_count":59},{"id":"1810.06394","title":"Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space","created":"2018-10-10","cited_by_count":58},{"id":"2011.13112","title":"Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Survey","created":"2020-11-26","cited_by_count":58},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58},{"id":"2302.03122","title":"State-wise Safe Reinforcement Learning: A Survey","created":"2023-02-06","cited_by_count":55},{"id":"2203.13168","title":"Model-Agnostic Multi-Agent Perception Framework","created":"2022-03-24","cited_by_count":51},{"id":"2103.14666","title":"Autonomous Overtaking in Gran Turismo Sport Using Curriculum Reinforcement Learning","created":"2021-03-26","cited_by_count":45},{"id":"2208.12397","title":"Causal Inference in Recommender Systems: A Survey and Future Directions","created":"2022-08-26","cited_by_count":44},{"id":"2410.05582","title":"Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-tuning","created":"2024-10-08","cited_by_count":42},{"id":"2105.05701","title":"Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic","created":"2021-05-12","cited_by_count":41},{"id":"1911.12250","title":"Social Attention for Autonomous Decision-Making in Dense Traffic","created":"2019-11-27","cited_by_count":39},{"id":"2003.01303","title":"Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization","created":"2020-03-03","cited_by_count":35},{"id":"2006.13704","title":"Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning with Application to Autonomous Driving","created":"2020-06-22","cited_by_count":34},{"id":"2502.19908","title":"CarPlanner: Consistent Auto-regressive Trajectory Planning for Large-scale Reinforcement Learning in Autonomous Driving","created":"2025-02-27","cited_by_count":34},{"id":"2309.05282","title":"Can you text what is happening? Integrating pre-trained language encoders into trajectory prediction models for autonomous driving","created":"2023-09-11","cited_by_count":30},{"id":"2407.13237","title":"LLM-Empowered State Representation for Reinforcement Learning","created":"2024-07-18","cited_by_count":28},{"id":"1608.08589","title":"Game-Theoretic Modeling of Driver and Vehicle Interactions for Verification and Validation of Autonomous Vehicle Control Systems","created":"2016-08-30","cited_by_count":24},{"id":"2004.06496","title":"Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning","created":"2020-04-11","cited_by_count":24},{"id":"2309.01909","title":"A Survey on Physics Informed Reinforcement Learning: Review and Open Problems","created":"2023-09-05","cited_by_count":24},{"id":"2403.19925","title":"Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces","created":"2024-03-29","cited_by_count":24},{"id":"2501.13072","title":"AdaWM: Adaptive World Model based Planning for Autonomous Driving","created":"2025-01-22","cited_by_count":24},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23},{"id":"1904.00035","title":"Autonomous Highway Driving using Deep Reinforcement Learning","created":"2019-03-29","cited_by_count":22},{"id":"1910.12905","title":"Deep Reinforcement Learning with Enhanced Safety for Autonomous Highway Driving","created":"2019-10-28","cited_by_count":21},{"id":"2102.11907","title":"A predictive safety filter for learning-based racing control","created":"2021-02-23","cited_by_count":20},{"id":"2404.08570","title":"Enhancing Autonomous Vehicle Training with Language Model Integration and Critical Scenario Generation","created":"2024-04-12","cited_by_count":19},{"id":"2011.04752","title":"Trajectory Planning for Autonomous Vehicles Using Hierarchical Reinforcement Learning","created":"2020-11-09","cited_by_count":17},{"id":"2111.04686","title":"Reinforcement Learning for Mixed Autonomy Intersections","created":"2021-11-08","cited_by_count":16},{"id":"2201.07833","title":"Hybrid Reinforcement Learning-Based Eco-Driving Strategy for Connected and Automated Vehicles at Signalized Intersections","created":"2022-01-19","cited_by_count":16},{"id":"2203.07676","title":"An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobility","created":"2022-03-15","cited_by_count":16},{"id":"2104.03111","title":"Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigation","created":"2021-04-07","cited_by_count":15},{"id":"2202.00881","title":"Robustness and Adaptability of Reinforcement Learning based Cooperative Autonomous Driving in Mixed-autonomy Traffic","created":"2022-02-02","cited_by_count":15},{"id":"2210.01041","title":"Probabilistic Safeguard for Reinforcement Learning Using Safety Index Guided Gaussian Process Models","created":"2022-10-03","cited_by_count":15},{"id":"2102.10643","title":"Safe Reinforcement Learning Using Robust Action Governor","created":"2021-02-21","cited_by_count":14},{"id":"2309.09408","title":"Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstration","created":"2023-09-18","cited_by_count":14},{"id":"2011.04697","title":"Behavior Planning at Urban Intersections through Hierarchical Reinforcement Learning","created":"2020-11-09","cited_by_count":12},{"id":"1908.00177","title":"Learning When to Drive in Intersections by Combining Reinforcement Learning and Model Predictive Control","created":"2019-08-01","cited_by_count":9},{"id":"2405.13547","title":"HighwayLLM: Decision-Making and Navigation in Highway Driving with RL-Informed Language Model","created":"2024-05-22","cited_by_count":9},{"id":"2003.11071","title":"Driver Modeling through Deep Reinforcement Learning and Behavioral Game Theory","created":"2020-03-24","cited_by_count":8},{"id":"2202.09644","title":"Multi-task Safe Reinforcement Learning for Navigating Intersections in Dense Traffic","created":"2022-02-19","cited_by_count":8},{"id":"2412.18511","title":"Large Language Model guided Deep Reinforcement Learning for Decision Making in Autonomous Driving","created":"2024-12-24","cited_by_count":8},{"id":"2008.12451","title":"Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles","created":"2020-08-28","cited_by_count":5},{"id":"2105.11299","title":"Fixed-Dimensional and Permutation Invariant State Representation of Autonomous Driving","created":"2021-05-24","cited_by_count":5},{"id":"2106.05639","title":"C-GLISp: Preference-Based Global Optimization under Unknown Constraints with Applications to Controller Calibration","created":"2021-06-10","cited_by_count":5},{"id":"2110.12359","title":"Self-learned Intelligence for Integrated Decision and Control of Automated Vehicles at Signalized Intersections","created":"2021-10-24","cited_by_count":5},{"id":"2108.13038","title":"Integrated Decision and Control at Multi-Lane Intersections with Mixed Traffic Flow","created":"2021-08-30","cited_by_count":4},{"id":"2203.04749","title":"Bilateral Deep Reinforcement Learning Approach for Better-than-human Car Following Model","created":"2022-03-03","cited_by_count":4},{"id":"2309.14209","title":"Continual Driving Policy Optimization with Closed-Loop Individualized Curricula","created":"2023-09-25","cited_by_count":4},{"id":"2207.13730","title":"Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control","created":"2022-07-27","cited_by_count":3},{"id":"2001.03864","title":"Learning to drive via Apprenticeship Learning and Deep Reinforcement Learning","created":"2020-01-12","cited_by_count":2},{"id":"2109.08993","title":"Geometric Task Networks: Learning Efficient and Explainable Skill Coordination for Object Manipulation","created":"2021-09-18","cited_by_count":2},{"id":"2305.13783","title":"Deep Reinforcement Learning-based Multi-objective Path Planning on the Off-road Terrain Environment for Ground Vehicles","created":"2023-05-23","cited_by_count":2},{"id":"2312.10557","title":"Improving Environment Robustness of Deep Reinforcement Learning Approaches for Autonomous Racing Using Bayesian Optimization-based Curriculum Learning","created":"2023-12-16","cited_by_count":2},{"id":"2405.07538","title":"Mirroring the Parking Target: An Optimal-Control-Based Parking Motion Planner with Strengthened Parking Reliability and Faster Parking Completion","created":"2024-05-13","cited_by_count":2},{"id":"2304.07984","title":"A Unified Safety Protection and Extension Governor","created":"2023-04-17","cited_by_count":1}],"next_cursor":null}