{"total":22,"rows":[{"id":"2106.06842","title":"Recomposing the Reinforcement Learning Building Blocks with Hypernetworks","created":"2021-06-12","cited_by_count":35,"area":null},{"id":"2201.08896","title":"Environment Generation for Zero-Shot Compositional Reinforcement Learning","created":"2022-01-21","cited_by_count":32,"area":null},{"id":"2406.01486","title":"Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos","created":"2024-06-03","cited_by_count":26,"area":null},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2302.08672","title":"Multimodal Subtask Graph Generation from Instructional Videos","created":"2023-02-17","cited_by_count":13,"area":null},{"id":"2109.07578","title":"Multi-Task Learning with Sequence-Conditioned Transporter Networks","created":"2021-09-15","cited_by_count":8,"area":null},{"id":"2301.12305","title":"Composing Task Knowledge with Modular Successor Feature Approximators","created":"2023-01-28","cited_by_count":7,"area":null},{"id":"2302.09173","title":"Unsupervised Task Graph Generation from Instructional Video Transcripts","created":"2023-02-17","cited_by_count":6,"area":null},{"id":"2307.03486","title":"Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning","created":"2023-07-07","cited_by_count":6,"area":null},{"id":"2203.12686","title":"Possibility Before Utility: Learning And Using Hierarchical Affordances","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2312.04668","title":"TOD-Flow: Modeling the Structure of Task-Oriented Dialogues","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2203.15034","title":"Learning Parameterized Task Structure for Generalization to Unseen Entities","created":"2022-03-28","cited_by_count":3,"area":null},{"id":"2205.12648","title":"Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2302.03364","title":"Population-size-Aware Policy Optimization for Mean-Field Games","created":"2023-02-07","cited_by_count":3,"area":null},{"id":"2311.09601","title":"Code Models are Zero-shot Precondition Reasoners","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2502.17753","title":"Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos","created":"2025-02-25","cited_by_count":2,"area":null},{"id":"2305.00508","title":"Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward","created":"2023-04-30","cited_by_count":1,"area":null},{"id":"2512.03479","title":"ProcObject-10K: Benchmarking Object-Centric Procedural Understanding in Instructional Videos","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2606.25317","title":"ESTANet: Efficient Online Error Detection in Procedural Videos via Prediction Inconsistency","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2112.08369","title":"Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning","created":"2021-12-15","cited_by_count":0,"area":null},{"id":"2206.05750","title":"Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning","created":"2022-06-12","cited_by_count":0,"area":null},{"id":"2301.07850","title":"Concept Discovery for Fast Adapatation","created":"2023-01-19","cited_by_count":0,"area":null}],"next_cursor":null}