{"total":12,"rows":[{"id":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41,"area":null},{"id":"2309.15257","title":"STARC: A General Framework For Quantifying Differences Between Reward Functions","created":"2023-09-26","cited_by_count":15,"area":null},{"id":"2408.05284","title":"Can a Bayesian Oracle Prevent Harm from an Agent?","created":"2024-08-09","cited_by_count":13,"area":null},{"id":"2310.02263","title":"Automatic Pair Construction for Contrastive Post-training","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2208.09570","title":"Calculus on MDPs: Potential Shaping as a Gradient","created":"2022-08-20","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":"2506.02923","title":"The Limits of Predicting Agents from Behaviour","created":"2025-06-03","cited_by_count":3,"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":"2403.06003","title":"A Generalized Acquisition Function for Preference-based Reward Learning","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2209.15320","title":"Bounded Robustness in Reinforcement Learning via Lexicographic Objectives","created":"2022-09-30","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":"2605.09217","title":"Learning the Preferences of a Learning Agent","created":"2026-05-09","cited_by_count":0,"area":null}],"next_cursor":null}