{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"1705.07057","title":"Masked Autoregressive Flow for Density Estimation","created":"2017-05-19","cited_by_count":684},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407},{"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":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290},{"id":"1810.05642","title":"The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems","created":"2018-10-11","cited_by_count":277},{"id":"2106.06926","title":"Bellman-consistent Pessimism for Offline Reinforcement Learning","created":"2021-06-13","cited_by_count":269},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"1910.03088","title":"INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps","created":"2019-09-30","cited_by_count":231},{"id":"1811.04820","title":"Learning from positive and unlabeled data: a survey","created":"2018-11-12","cited_by_count":219},{"id":"2311.01455","title":"RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation","created":"2023-11-02","cited_by_count":218},{"id":"2106.12142","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","created":"2021-06-23","cited_by_count":193},{"id":"2104.12225","title":"DC3: A learning method for optimization with hard constraints","created":"2021-04-25","cited_by_count":184},{"id":"1803.08533","title":"Understanding Measures of Uncertainty for Adversarial Example Detection","created":"2018-03-22","cited_by_count":177},{"id":"1910.13393","title":"Constrained Reinforcement Learning Has Zero Duality Gap","created":"2019-10-29","cited_by_count":151},{"id":"1911.07602","title":"The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersections","created":"2019-11-18","cited_by_count":137},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121},{"id":"2006.12007","title":"Near-Optimal Reinforcement Learning with Self-Play","created":"2020-06-22","cited_by_count":109},{"id":"2202.02215","title":"A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective","created":"2022-02-04","cited_by_count":105},{"id":"2109.14523","title":"Online Robust Reinforcement Learning with Model Uncertainty","created":"2021-09-29","cited_by_count":96},{"id":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96},{"id":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91},{"id":"1802.07127","title":"Actions Speak Louder Than Goals: Valuing Player Actions in Soccer","created":"2018-02-18","cited_by_count":90},{"id":"2202.06239","title":"Supported Policy Optimization for Offline Reinforcement Learning","created":"2022-02-13","cited_by_count":74},{"id":"2110.04184","title":"When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?","created":"2021-10-08","cited_by_count":67},{"id":"2202.10341","title":"Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization","created":"2022-02-17","cited_by_count":49},{"id":"2403.02475","title":"Enhancing LLM Safety via Constrained Direct Preference Optimization","created":"2024-03-04","cited_by_count":49},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48},{"id":"2011.09999","title":"Inverse Constrained Reinforcement Learning","created":"2020-11-19","cited_by_count":46},{"id":"1901.02739","title":"Dirichlet Variational Autoencoder","created":"2019-01-09","cited_by_count":43},{"id":"1909.05477","title":"Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning","created":"2019-09-12","cited_by_count":34},{"id":"2007.01174","title":"Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch","created":"2020-07-02","cited_by_count":33},{"id":"2207.08645","title":"Active Exploration for Inverse Reinforcement Learning","created":"2022-07-18","cited_by_count":27},{"id":"2405.18418","title":"Hierarchical World Models as Visual Whole-Body Humanoid Controllers","created":"2024-05-28","cited_by_count":27},{"id":"2302.07457","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","created":"2023-02-15","cited_by_count":26},{"id":"1805.11088","title":"Deep Reinforcement Learning in Ice Hockey for Context-Aware Player Evaluation","created":"2018-05-26","cited_by_count":23},{"id":"2304.12966","title":"Towards Theoretical Understanding of Inverse Reinforcement Learning","created":"2023-04-25","cited_by_count":21},{"id":"2303.02430","title":"CFlowNets: Continuous Control with Generative Flow Networks","created":"2023-03-04","cited_by_count":19},{"id":"2305.16147","title":"Learning Safety Constraints from Demonstrations with Unknown Rewards","created":"2023-05-25","cited_by_count":19},{"id":"2206.09670","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","created":"2022-06-20","cited_by_count":18},{"id":"2306.00629","title":"Identifiability and Generalizability in Constrained Inverse Reinforcement Learning","created":"2023-06-01","cited_by_count":16},{"id":"2102.12554","title":"Maximum Likelihood Constraint Inference from Stochastic Demonstrations","created":"2021-02-24","cited_by_count":15},{"id":"2309.00711","title":"Learning Shared Safety Constraints from Multi-task Demonstrations","created":"2023-09-01","cited_by_count":15},{"id":"2203.11409","title":"A Primer on Maximum Causal Entropy Inverse Reinforcement Learning","created":"2022-03-22","cited_by_count":13},{"id":"2206.01311","title":"Learning Soft Constraints From Constrained Expert Demonstrations","created":"2022-06-02","cited_by_count":13},{"id":"2305.13681","title":"GUARD: A Safe Reinforcement Learning Benchmark","created":"2023-05-23","cited_by_count":13},{"id":"1910.03477","title":"Learning Parametric Constraints in High Dimensions from Demonstrations","created":"2019-10-08","cited_by_count":10},{"id":"2011.04141","title":"Uncertainty-Aware Constraint Learning for Adaptive Safe Motion Planning from Demonstrations","created":"2020-11-09","cited_by_count":10},{"id":"2110.12468","title":"False Correlation Reduction for Offline Reinforcement Learning","created":"2021-10-24","cited_by_count":9},{"id":"2309.08571","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning","created":"2023-09-15","cited_by_count":9},{"id":"2109.11018","title":"Making Human-Like Trade-offs in Constrained Environments by Learning from Demonstrations","created":"2021-09-22","cited_by_count":7},{"id":"2305.02857","title":"Maximum Causal Entropy Inverse Constrained Reinforcement Learning","created":"2023-05-04","cited_by_count":7},{"id":"2003.03912","title":"Online inverse reinforcement learning with unknown disturbances","created":"2020-03-09","cited_by_count":6},{"id":"2406.16782","title":"Confidence Aware Inverse Constrained Reinforcement Learning","created":"2024-06-24","cited_by_count":6},{"id":"2203.11842","title":"X-MEN: Guaranteed XOR-Maximum Entropy Constrained Inverse Reinforcement Learning","created":"2022-03-22","cited_by_count":4},{"id":"2403.02431","title":"Bayesian Constraint Inference from User Demonstrations Based on Margin-Respecting Preference Models","created":"2024-03-04","cited_by_count":4},{"id":"2304.03367","title":"Constraint Inference in Control Tasks from Expert Demonstrations via Inverse Optimization","created":"2023-04-06","cited_by_count":2},{"id":"2311.09439","title":"Learning Hyperplanes for Multi-Agent Collision Avoidance in Space","created":"2023-11-15","cited_by_count":2}],"next_cursor":null}