{"total":16,"rows":[{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46,"area":null},{"id":"2212.04717","title":"On the Sensitivity of Reward Inference to Misspecified Human Models","created":"2022-12-09","cited_by_count":25,"area":null},{"id":"2212.01174","title":"Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning","created":"2022-12-02","cited_by_count":8,"area":null},{"id":"2302.11996","title":"K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs","created":"2023-02-23","cited_by_count":6,"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":"2308.08427","title":"Eliciting Risk Aversion with Inverse Reinforcement Learning via Interactive Questioning","created":"2023-08-16","cited_by_count":2,"area":null},{"id":"2508.00159","title":"Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2302.09676","title":"Leveraging Prior Knowledge in Reinforcement Learning via Double-Sided Bounds on the Value Function","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2405.15975","title":"Inference of Utilities and Time Preference in Sequential Decision-Making","created":"2024-05-24","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":"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":"2604.07480","title":"Active Reward Machine Inference From Raw State Trajectories","created":"2026-04-08","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},{"id":"2608.08240","title":"A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2609.13469","title":"Inverse Learning of the Altruism and Cost Level in Mixed-Individual Mean Field Games","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}