{"url":"/task/hierarchical-reinforcement-learning","name":"Hierarchical Reinforcement Learning","slug":"hierarchical-reinforcement-learning","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":384,"papers_with_code":111,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/hierarchical-reinforcement-learning-on-ant","slug":"hierarchical-reinforcement-learning-on-ant","dataset":"Ant + Maze","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"STAR","paper_title":"Reconciling Spatial and Temporal Abstractions for Goal Representation","paper_url":"/paper/reconciling-spatial-and-temporal-abstractions","paper_date":"2024-01-18","arxiv_id":"2401.09870","code_links":[{"title":"cosynus-lix/STAR","url":"https://github.com/cosynus-lix/STAR"}],"syntology":{"n":11,"n_ran":5,"n_unverified":6,"n_pointer_only":11}}}],"datasets":[{"url":"/dataset/gibson-environment","name":"Gibson Environment","full_name":"","num_papers_in_archive":22},{"url":"/dataset/bipedal-skills","name":"bipedal-skills","full_name":"Bipedal Skills Benchmark for Reinforcement Learning","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":111,"tagged_in_all":384,"items":[{"url":"/paper/a-tutorial-on-bayesian-optimization-of","title":"A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning","date":"2010-12-12","arxiv_id":"1012.2599","repositories_listed":15,"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/data-efficient-hierarchical-reinforcement","title":"Data-Efficient Hierarchical Reinforcement Learning","date":"2018-05-21","arxiv_id":"1805.08296","repositories_listed":12,"syntology":null},{"url":"/paper/near-optimal-representation-learning-for","title":"Near-Optimal Representation Learning for Hierarchical Reinforcement Learning","date":"2018-10-02","arxiv_id":"1810.01257","repositories_listed":6,"syntology":null},{"url":"/paper/hierarchical-reinforcement-learning-with-the","title":"Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition","date":"1999-05-21","arxiv_id":"cs/9905014","repositories_listed":5,"syntology":null},{"url":"/paper/task-oriented-dialogue-system-for-automatic-1","title":"Hierarchical Reinforcement Learning for Automatic Disease Diagnosis","date":"2020-04-29","arxiv_id":"2004.14254","repositories_listed":4,"syntology":null},{"url":"/paper/learning-multi-level-hierarchies-with","title":"Learning Multi-Level Hierarchies with Hindsight","date":"2017-12-04","arxiv_id":"1712.00948","repositories_listed":4,"syntology":null},{"url":"/paper/reasonflux-hierarchical-llm-reasoning-via","title":"ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates","date":"2025-02-10","arxiv_id":"2502.06772","repositories_listed":3,"syntology":null},{"url":"/paper/step-by-step-a-hierarchical-framework-for","title":"Step by step: a hierarchical framework for multi-hop knowledge graph reasoning with reinforcement learning","date":"2022-07-19","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/hg2p-hippocampus-inspired-high-reward-graph","title":"HG2P: Hippocampus-inspired High-reward Graph and Model-Free Q-Gradient Penalty for Path Planning and Motion Control","date":"2024-10-12","arxiv_id":"2410.09505","repositories_listed":2,"syntology":null},{"url":"/paper/joint-admission-control-and-resource","title":"Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning","date":"2024-06-25","arxiv_id":"2406.17334","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":7}},{"url":"/paper/towards-automated-imbalanced-learning-with","title":"Towards Automated Imbalanced Learning with Deep Hierarchical Reinforcement Learning","date":"2022-08-26","arxiv_id":"2208.12433","repositories_listed":2,"syntology":null},{"url":"/paper/online-baum-welch-algorithm-for-hierarchical","title":"Online Baum-Welch algorithm for Hierarchical Imitation Learning","date":"2021-03-22","arxiv_id":"2103.12197","repositories_listed":2,"syntology":null},{"url":"/paper/modelling-hierarchical-structure-between","title":"Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System","date":"2020-06-11","arxiv_id":"2006.06814","repositories_listed":2,"syntology":null},{"url":"/paper/combinatorial-optimization-by-graph-pointer","title":"Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning","date":"2019-11-12","arxiv_id":"1911.04936","repositories_listed":2,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/learning-fairness-in-multi-agent-systems","title":"Learning Fairness in Multi-Agent Systems","date":"2019-10-31","arxiv_id":"1910.14472","repositories_listed":2,"syntology":null},{"url":"/paper/learning-goal-embeddings-via-self-play-for","title":"Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning","date":"2018-11-22","arxiv_id":"1811.09083","repositories_listed":2,"syntology":null},{"url":"/paper/a-hierarchical-framework-for-relation","title":"A Hierarchical Framework for Relation Extraction with Reinforcement Learning","date":"2018-11-09","arxiv_id":"1811.03925","repositories_listed":2,"syntology":null},{"url":"/paper/stochastic-neural-networks-for-hierarchical","title":"Stochastic Neural Networks for Hierarchical Reinforcement Learning","date":"2017-04-10","arxiv_id":"1704.03012","repositories_listed":2,"syntology":null},{"url":"/paper/skillblender-towards-versatile-humanoid-whole","title":"SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending","date":"2025-06-11","arxiv_id":"2506.09366","repositories_listed":1,"syntology":null},{"url":"/paper/from-debate-to-equilibrium-belief-driven","title":"From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium","date":"2025-06-09","arxiv_id":"2506.08292","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/divide-and-conquer-grounding-llms-as","title":"Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning","date":"2025-05-26","arxiv_id":"2505.19761","repositories_listed":1,"syntology":null},{"url":"/paper/implicitly-aligning-humans-and-autonomous","title":"Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions","date":"2025-05-07","arxiv_id":"2505.04579","repositories_listed":1,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/solving-sokoban-using-hierarchical-1","title":"Solving Sokoban using Hierarchical Reinforcement Learning with Landmarks","date":"2025-04-06","arxiv_id":"2504.04366","repositories_listed":1,"syntology":null},{"url":"/paper/learning-with-expert-abstractions-for","title":"Learning with Expert Abstractions for Efficient Multi-Task Continuous Control","date":"2025-03-19","arxiv_id":"2503.14809","repositories_listed":1,"syntology":null},{"url":"/paper/multi-turn-code-generation-through-single","title":"Multi-Turn Code Generation Through Single-Step Rewards","date":"2025-02-27","arxiv_id":"2502.20380","repositories_listed":1,"syntology":null},{"url":"/paper/tag-a-decentralized-framework-for-multi-agent","title":"TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning","date":"2025-02-21","arxiv_id":"2502.15425","repositories_listed":1,"syntology":null},{"url":"/paper/autonomous-option-invention-for-continual","title":"Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning","date":"2024-12-20","arxiv_id":"2412.16395","repositories_listed":1,"syntology":null},{"url":"/paper/meta-learning-integration-in-hierarchical","title":"Meta-Learning Integration in Hierarchical Reinforcement Learning for Advanced Task Complexity","date":"2024-10-10","arxiv_id":"2410.07921","repositories_listed":1,"syntology":null},{"url":"/paper/selective-exploration-and-information","title":"Selective Exploration and Information Gathering in Search and Rescue Using Hierarchical Learning Guided by Natural Language Input","date":"2024-09-20","arxiv_id":"2409.13445","repositories_listed":1,"syntology":null},{"url":"/paper/item-difficulty-aware-learning-path","title":"Item-Difficulty-Aware Learning Path Recommendation: From a Real Walking Perspective","date":"2024-08-24","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}