{"total":20,"rows":[{"id":"2101.06521","title":"Hierarchical Reinforcement Learning By Discovering Intrinsic Options","created":"2021-01-16","cited_by_count":58,"area":null},{"id":"2206.10680","title":"Learning Neuro-Symbolic Skills for Bilevel Planning","created":"2022-06-21","cited_by_count":58,"area":null},{"id":"2205.14691","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2412.19726","title":"Position: Theory of Mind Benchmarks are Broken for Large Language Models","created":"2024-12-27","cited_by_count":31,"area":null},{"id":"2111.03189","title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","created":"2021-11-04","cited_by_count":26,"area":null},{"id":"2112.03097","title":"Flexible Option Learning","created":"2021-12-06","cited_by_count":25,"area":null},{"id":"2209.01947","title":"MO2: Model-Based Offline Options","created":"2022-09-05","cited_by_count":10,"area":null},{"id":"2109.09876","title":"Context-Specific Representation Abstraction for Deep Option Learning","created":"2021-09-20","cited_by_count":8,"area":null},{"id":"2201.02628","title":"Attention Option-Critic","created":"2022-01-07","cited_by_count":8,"area":null},{"id":"2106.03853","title":"DisTop: Discovering a Topological representation to learn diverse and rewarding skills","created":"2021-06-06","cited_by_count":7,"area":null},{"id":"2302.00671","title":"QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing","created":"2023-02-01","cited_by_count":6,"area":null},{"id":"2306.09980","title":"Creating Multi-Level Skill Hierarchies in Reinforcement Learning","created":"2023-06-16","cited_by_count":5,"area":null},{"id":"2201.08115","title":"Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning","created":"2022-01-20","cited_by_count":3,"area":null},{"id":"2512.19154","title":"Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2512.22337","title":"The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Models","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2606.20363","title":"Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2102.00572","title":"Interpretable Reinforcement Learning Inspired by Piaget's Theory of Cognitive Development","created":"2021-02-01","cited_by_count":0,"area":null},{"id":"2205.10607","title":"Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel","created":"2022-05-21","cited_by_count":0,"area":null},{"id":"2212.11726","title":"Reusable Options through Gradient-based Meta Learning","created":"2022-12-22","cited_by_count":0,"area":null},{"id":"2609.05508","title":"When Do Options Help? Policy Necrosis and Redundant Coverage in Option-Critic","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}