{"total":22,"rows":[{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"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":"2602.05031","title":"Laplacian Representations for Decision-Time Planning","created":"2026-02-04","cited_by_count":5,"area":"deeprl"},{"id":"2412.16395","title":"Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning","created":"2024-12-20","cited_by_count":4,"area":"deeprl"},{"id":"2505.16217","title":"Reward-Aware Proto-Representations in Reinforcement Learning","created":"2025-05-22","cited_by_count":4,"area":"deeprl"},{"id":"2507.20853","title":"Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces","created":"2025-07-28","cited_by_count":3,"area":"deeprl"},{"id":"2406.07897","title":"When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions","created":"2024-06-12","cited_by_count":2,"area":"deeprl"},{"id":"2412.08574","title":"Sketch Decompositions for Classical Planning via Deep Reinforcement Learning","created":"2024-12-11","cited_by_count":2,"area":"deeprl"},{"id":"2505.12508","title":"InnateCoder: Learning Programmatic Options with Foundation Models","created":"2025-05-18","cited_by_count":2,"area":"deeprl"},{"id":"2509.02930","title":"VendiRL: A Framework for Self-Supervised Reinforcement Learning of Diversely Diverse Skills","created":"2025-09-03","cited_by_count":2,"area":"deeprl"},{"id":"2412.16687","title":"Subgoal Discovery Using a Free Energy Paradigm and State Aggregations","created":"2024-12-21","cited_by_count":1,"area":"deeprl"},{"id":"2406.18053","title":"Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies","created":"2024-06-26","cited_by_count":0,"area":"deeprl"},{"id":"2409.11756","title":"Synthesizing Evolving Symbolic Representations for Autonomous Systems","created":"2024-09-18","cited_by_count":0,"area":"deeprl"},{"id":"2505.15754","title":"Improving planning and MBRL with temporally-extended actions","created":"2025-05-21","cited_by_count":0,"area":"deeprl"},{"id":"2510.24988","title":"Enhancing Hierarchical Reinforcement Learning through Change Point Detection in Time Series","created":"2025-10-28","cited_by_count":0,"area":"deeprl"},{"id":"2512.04958","title":"Realizable Abstractions: Near-Optimal Hierarchical Reinforcement Learning","created":"2025-12-04","cited_by_count":0,"area":"deeprl"},{"id":"2601.21391","title":"Intrinsic Reward Policy Optimization for Sparse-Reward Environments","created":"2026-01-29","cited_by_count":0,"area":"deeprl"},{"id":"2604.07016","title":"Predictive Representations for Skill Transfer in Reinforcement Learning","created":"2026-04-08","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"},{"id":"2606.00427","title":"Topology-Aware State Abstraction with Tangle Cores for Markov Decision Processes","created":"2026-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2609.06186","title":"Spectral Prioritized Sweeping in Nonstationary Reinforcement Learning","created":"2026-09-05","cited_by_count":0,"area":"deeprl"},{"id":"2610.03604","title":"Mastering Atari 2600 Games with Discovered Options","created":"2026-10-02","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}