{"total":109,"rows":[{"id":"2108.00941","title":"A Survey of Human-in-the-loop for Machine Learning","created":"2021-08-02","cited_by_count":215,"area":null},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2308.12270","title":"Language Reward Modulation for Pretraining Reinforcement Learning","created":"2023-08-23","cited_by_count":43,"area":null},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2105.01099","title":"Reinforcement Learning for Ridesharing: An Extended Survey","created":"2021-05-03","cited_by_count":35,"area":null},{"id":"2108.11092","title":"INVIGORATE: Interactive Visual Grounding and Grasping in Clutter","created":"2021-08-25","cited_by_count":32,"area":null},{"id":"2109.00127","title":"Cognitive science as a source of forward and inverse models of human decisions for robotics and control","created":"2021-09-01","cited_by_count":22,"area":null},{"id":"2311.02379","title":"Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models","created":"2023-11-04","cited_by_count":22,"area":null},{"id":"2203.12592","title":"Your Policy Regularizer is Secretly an Adversary","created":"2022-03-23","cited_by_count":21,"area":null},{"id":"2106.14015","title":"Contextual Inverse Optimization: Offline and Online Learning","created":"2021-06-26","cited_by_count":20,"area":null},{"id":"2405.13242","title":"Goals as Reward-Producing Programs","created":"2024-05-21","cited_by_count":14,"area":null},{"id":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2401.00298","title":"Principal-Agent Reward Shaping in MDPs","created":"2023-12-30","cited_by_count":13,"area":null},{"id":"2109.08947","title":"Risk-averse autonomous systems: A brief history and recent developments from the perspective of optimal control","created":"2021-09-18","cited_by_count":12,"area":null},{"id":"2104.06411","title":"Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning","created":"2021-04-13","cited_by_count":11,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2301.12351","title":"Emerging Synergies in Causality and Deep Generative Models: A Survey","created":"2023-01-29","cited_by_count":10,"area":null},{"id":"2501.07468","title":"From Screens to Scenes: A Survey of Embodied AI in Healthcare","created":"2025-01-13","cited_by_count":10,"area":null},{"id":"2211.15823","title":"Personalized Reward Learning with Interaction-Grounded Learning (IGL)","created":"2022-11-28","cited_by_count":9,"area":null},{"id":"2402.01344","title":"Monotone, Bi-Lipschitz, and Polyak-Lojasiewicz Networks","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2412.05515","title":"Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning","created":"2024-12-07","cited_by_count":9,"area":null},{"id":"2107.09598","title":"Learning Altruistic Behaviours in Reinforcement Learning without External Rewards","created":"2021-07-20","cited_by_count":8,"area":null},{"id":"2211.03408","title":"RITA: Boost Driving Simulators with Realistic Interactive Traffic Flow","created":"2022-11-07","cited_by_count":7,"area":null},{"id":"2301.00188","title":"New Challenges in Reinforcement Learning: A Survey of Security and Privacy","created":"2022-12-31","cited_by_count":7,"area":null},{"id":"2312.14106","title":"Learning Human-like Representations to Enable Learning Human Values","created":"2023-12-21","cited_by_count":7,"area":null},{"id":"2212.09917","title":"Inverse Reinforcement Learning for Text Summarization","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2305.16913","title":"Acting as Inverse Inverse Planning","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2310.14092","title":"Learning Reward for Physical Skills using Large Language Model","created":"2023-10-21","cited_by_count":5,"area":null},{"id":"2103.04727","title":"Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning","created":"2021-03-08","cited_by_count":4,"area":null},{"id":"2202.07364","title":"Zero-Shot Assistance in Sequential Decision Problems","created":"2022-02-15","cited_by_count":4,"area":null},{"id":"2205.15376","title":"Reinforcement Learning with a Terminator","created":"2022-05-30","cited_by_count":4,"area":null},{"id":"2304.03984","title":"DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning","created":"2023-04-08","cited_by_count":4,"area":null},{"id":"2305.17195","title":"Inferring the Future by Imagining the Past","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2504.05755","title":"Unraveling Human-AI Teaming: A Review and Outlook","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2109.07788","title":"Marginal MAP Estimation for Inverse RL under Occlusion with Observer Noise","created":"2021-09-16","cited_by_count":3,"area":null},{"id":"2112.15331","title":"Using Graph-Aware Reinforcement Learning to Identify Winning Strategies in Diplomacy Games (Student Abstract)","created":"2021-12-31","cited_by_count":3,"area":null},{"id":"2208.14788","title":"Negative Human Rights as a Basis for Long-term AI Safety and Regulation","created":"2022-08-31","cited_by_count":3,"area":null},{"id":"2306.11128","title":"CAMMARL: Conformal Action Modeling in Multi Agent Reinforcement Learning","created":"2023-06-19","cited_by_count":3,"area":null},{"id":"2311.08393","title":"MVSA-Net: Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation","created":"2023-11-14","cited_by_count":3,"area":null},{"id":"2410.00436","title":"Task Success Prediction for Open-Vocabulary Manipulation Based on Multi-Level Aligned Representations","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2505.15863","title":"Generative AI for Autonomous Driving: A Review","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2511.15055","title":"Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2103.15171","title":"A Bayesian Approach to Identifying Representational Errors","created":"2021-03-28","cited_by_count":2,"area":null},{"id":"2206.01192","title":"Uniqueness and Complexity of Inverse MDP Models","created":"2022-06-02","cited_by_count":2,"area":null},{"id":"2206.14267","title":"Applications of Reinforcement Learning in Finance -- Trading with a Double Deep Q-Network","created":"2022-06-28","cited_by_count":2,"area":null},{"id":"2304.10590","title":"A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making","created":"2023-04-20","cited_by_count":2,"area":null},{"id":"2305.19421","title":"Data and Knowledge for Overtaking Scenarios in Autonomous Driving","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2306.12609","title":"Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities","created":"2023-06-22","cited_by_count":2,"area":null},{"id":"2308.08427","title":"Eliciting Risk Aversion with Inverse Reinforcement Learning via Interactive Questioning","created":"2023-08-16","cited_by_count":2,"area":null},{"id":"2309.12560","title":"Machine Learning Meets Advanced Robotic Manipulation","created":"2023-09-22","cited_by_count":2,"area":null},{"id":"2311.11537","title":"ADAPTER-RL: Adaptation of Any Agent using Reinforcement Learning","created":"2023-11-20","cited_by_count":2,"area":null},{"id":"2410.12172","title":"The State of Robot Motion Generation","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2412.02570","title":"TAB-Fields: A Maximum Entropy Framework for Mission-Aware Adversarial Planning","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2106.06515","title":"Probability Paths and the Structure of Predictions over Time","created":"2021-06-11","cited_by_count":1,"area":null},{"id":"2112.15221","title":"Constraint Sampling Reinforcement Learning: Incorporating Expertise For Faster Learning","created":"2021-12-30","cited_by_count":1,"area":null},{"id":"2204.12605","title":"Zero-Touch Network on Industrial IoT: An End-to-End Machine Learning Approach","created":"2022-04-26","cited_by_count":1,"area":null},{"id":"2205.06485","title":"Modeling Human Behavior Part I -- Learning and Belief Approaches","created":"2022-05-13","cited_by_count":1,"area":null},{"id":"2207.00868","title":"The Linguistic Blind Spot of Value-Aligned Agency, Natural and Artificial","created":"2022-07-02","cited_by_count":1,"area":null},{"id":"2212.08961","title":"Training Robots to Evaluate Robots: Example-Based Interactive Reward Functions for Policy Learning","created":"2022-12-17","cited_by_count":1,"area":null},{"id":"2303.09027","title":"Learning Rewards to Optimize Global Performance Metrics in Deep Reinforcement Learning","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2303.13489","title":"Boosting Reinforcement Learning and Planning with Demonstrations: A Survey","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2304.12241","title":"Positive AI: Key Challenges in Designing Artificial Intelligence for Wellbeing","created":"2023-04-12","cited_by_count":1,"area":null},{"id":"2306.10345","title":"Do as I can, not as I get","created":"2023-06-17","cited_by_count":1,"area":null},{"id":"2307.16387","title":"Relation-First Modeling Paradigm for Causal Representation Learning toward the Development of AGI","created":"2023-07-31","cited_by_count":1,"area":null},{"id":"2309.16960","title":"On Generating Explanations for Reinforcement Learning Policies: An Empirical Study","created":"2023-09-29","cited_by_count":1,"area":null},{"id":"2310.15333","title":"Safe and Interpretable Estimation of Optimal Treatment Regimes","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2311.16807","title":"Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning","created":"2023-11-28","cited_by_count":1,"area":null},{"id":"2403.08199","title":"Deep Submodular Peripteral Networks","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2405.01261","title":"Continuously evolving rewards in an open-ended environment","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2409.13299","title":"OMG-RL:Offline Model-based Guided Reward Learning for Heparin Treatment","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2412.11360","title":"Visual IRL for Human-Like Robotic Manipulation","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2502.15716","title":"Feature-Aware Task-to-Core Allocation in Embedded Multi-core Platforms via Statistical Learning","created":"2025-01-26","cited_by_count":1,"area":null},{"id":"2112.11014","title":"fMRI Neurofeedback Learning Patterns are Predictive of Personal and Clinical Traits","created":"2021-12-21","cited_by_count":0,"area":null},{"id":"2204.01975","title":"GAIL-PT: A Generic Intelligent Penetration Testing Framework with Generative Adversarial Imitation Learning","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2302.04608","title":"Differentially Private Deep Q-Learning for Pattern Privacy Preservation in MEC Offloading","created":"2023-02-09","cited_by_count":0,"area":null},{"id":"2302.13268","title":"Revolutionizing Genomics with Reinforcement Learning Techniques","created":"2023-02-26","cited_by_count":0,"area":null},{"id":"2304.13863","title":"Ensoul: A framework for the creation of self organizing intelligent ultra low power systems (SOULS) through evolutionary enerstatic networks","created":"2023-04-26","cited_by_count":0,"area":null},{"id":"2307.08532","title":"LuckyMera: a Modular AI Framework for Building Hybrid NetHack Agents","created":"2023-07-17","cited_by_count":0,"area":null},{"id":"2311.12004","title":"Risk-averse Batch Active Inverse Reward Design","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2312.10328","title":"Deriving Rewards for Reinforcement Learning from Symbolic Behaviour Descriptions of Bipedal Walking","created":"2023-12-16","cited_by_count":0,"area":null},{"id":"2401.00330","title":"Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions","created":"2023-12-30","cited_by_count":0,"area":null},{"id":"2402.07462","title":"A Hormetic Approach to the Value-Loading Problem: Preventing the Paperclip Apocalypse?","created":"2024-02-12","cited_by_count":0,"area":null},{"id":"2406.11984","title":"Online Pareto-Optimal Decision-Making for Complex Tasks using Active Inference","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2406.16748","title":"OCALM: Object-Centric Assessment with Language Models","created":"2024-06-24","cited_by_count":0,"area":null},{"id":"2409.14191","title":"Addressing and Visualizing Misalignments in Human Task-Solving Trajectories","created":"2024-09-21","cited_by_count":0,"area":null},{"id":"2411.00156","title":"Unlocking the Potential of Global Human Expertise","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2411.03131","title":"Machine Learning Innovations in CPR: A Comprehensive Survey on Enhanced Resuscitation Techniques","created":"2024-11-03","cited_by_count":0,"area":null},{"id":"2501.06376","title":"Robustness in the Face of Partial Identifiability in Reward Learning","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2505.20342","title":"Machine Theory of Mind and the Structure of Human Values","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2508.04269","title":"A Visual Tool for Interactive Model Explanation using Sensitivity Analysis","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2511.05640","title":"Blind Inverse Game Theory: Jointly Decoding Rewards and Rationality in Entropy-Regularized Competitive Games","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2601.08166","title":"ZeroDVFS: Zero-Shot LLM-Guided Core and Frequency Allocation for Embedded Platforms","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2601.22292","title":"Learning Incentive Structures for Cooperative Resilience in Multi-Agent Systems under Social Dilemmas","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.02838","title":"Beyond Content: Behavioral Policies Reveal Actors in Information Operations","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.16099","title":"Quantifying and Attributing Submodel Uncertainty in Stochastic Simulation Models and Digital Twins","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.02259","title":"The Alignment Flywheel: A Governance-Centric Hybrid MAS for Architecture-Agnostic Safety","created":"2026-02-28","cited_by_count":0,"area":null}],"next_cursor":"100"}