{"total":14,"rows":[{"id":"2411.19418","title":"Proto Successor Measure: Representing the Behavior Space of an RL Agent","created":"2024-11-29","cited_by_count":20,"area":"deeprl"},{"id":"2410.22133","title":"Learning Successor Features the Simple Way","created":"2024-10-29","cited_by_count":10,"area":"deeprl"},{"id":"2506.10629","title":"Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning","created":"2025-06-12","cited_by_count":5,"area":"deeprl"},{"id":"2402.02665","title":"Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning","created":"2024-02-05","cited_by_count":4,"area":"deeprl"},{"id":"2403.15301","title":"Planning with a Learned Policy Basis to Optimally Solve Complex Tasks","created":"2024-03-22","cited_by_count":4,"area":"deeprl"},{"id":"2410.02236","title":"C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front","created":"2024-10-03","cited_by_count":4,"area":"deeprl"},{"id":"2411.18195","title":"Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance","created":"2024-11-27","cited_by_count":4,"area":"deeprl"},{"id":"2404.03997","title":"Demonstration Guided Multi-Objective Reinforcement Learning","created":"2024-04-05","cited_by_count":2,"area":"deeprl"},{"id":"2407.11489","title":"A Meta-Learning Approach for Multi-Objective Reinforcement Learning in Sustainable Home Environments","created":"2024-07-16","cited_by_count":2,"area":"deeprl"},{"id":"2505.00787","title":"Constructing an Optimal Behavior Basis for the Option Keyboard","created":"2025-05-01","cited_by_count":2,"area":"deeprl"},{"id":"2604.24532","title":"A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning","created":"2026-04-27","cited_by_count":2,"area":"deeprl"},{"id":"2506.04022","title":"Interpretability by Design for Efficient Multi-Objective Reinforcement Learning","created":"2025-06-04","cited_by_count":0,"area":"deeprl"},{"id":"2511.16476","title":"Limitations of Scalarisation in MORL: A Comparative Study in Discrete Environments","created":"2025-11-20","cited_by_count":0,"area":"deeprl"},{"id":"2605.31289","title":"The Terminal Representation in Reinforcement Learning","created":"2026-05-29","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}