{"total":22,"rows":[{"id":"2304.03279","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","created":"2023-04-06","cited_by_count":182,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2206.15474","title":"Forecasting Future World Events with Neural Networks","created":"2022-06-30","cited_by_count":63,"area":null},{"id":"2110.13136","title":"What Would Jiminy Cricket Do? Towards Agents That Behave Morally","created":"2021-10-25","cited_by_count":57,"area":null},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21,"area":null},{"id":"2201.07082","title":"Inducing Structure in Reward Learning by Learning Features","created":"2022-01-18","cited_by_count":16,"area":null},{"id":"2302.13137","title":"A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors","created":"2023-02-25","cited_by_count":15,"area":null},{"id":"2111.05251","title":"Learning Perceptual Concepts by Bootstrapping from Human Queries","created":"2021-11-09","cited_by_count":12,"area":null},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2301.10095","title":"Large Language Models as Fiduciaries: A Case Study Toward Robustly Communicating With Artificial Intelligence Through Legal Standards","created":"2023-01-24","cited_by_count":8,"area":null},{"id":"2111.09884","title":"Assisted Robust Reward Design","created":"2021-11-18","cited_by_count":5,"area":null},{"id":"2206.00152","title":"Human-AI Shared Control via Policy Dissection","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2110.14615","title":"Play to Grade: Testing Coding Games as Classifying Markov Decision Process","created":"2021-10-27","cited_by_count":3,"area":null},{"id":"2112.09169","title":"On Optimizing Interventions in Shared Autonomy","created":"2021-12-16","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":"2105.11977","title":"Towards Teachable Autotelic Agents","created":"2021-05-25","cited_by_count":2,"area":null},{"id":"2402.06501","title":"Scalable Interactive Machine Learning for Future Command and Control","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2203.06290","title":"SOCKS: A Stochastic Optimal Control and Reachability Toolbox Using Kernel Methods","created":"2022-03-12","cited_by_count":1,"area":null},{"id":"2608.23311","title":"Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.34126","title":"JET: Judge-Guided Evolution at Test Time for Agent Programs","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}