{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":11,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/reconciling-spatial-and-temporal-abstractions#ran","syntology_url":"https://syntology.ai/paper/2401.09870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09870"}},"official":{"repos":["cosynus-lix/STAR"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}}}],"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":384,"of_with_code":111,"tagged_in_all":384,"counts":{"archive_papers_tagged":384,"with_a_code_link":111,"where_syntology_ran_a_sample":22,"not_listed_spam_title":0,"listed":384,"listed_where_code_ran":22,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":22,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":22,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/a-tutorial-on-bayesian-optimization-of","slug":"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":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-tutorial-on-bayesian-optimization-of#ran","syntology_url":"https://syntology.ai/paper/1012.2599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1012.2599"}},"official":null}},{"url":"/paper/data-efficient-hierarchical-reinforcement","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/joint-admission-control-and-resource#ran","syntology_url":"https://syntology.ai/paper/2406.17334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17334"}},"official":{"repos":["geminilight/hrl-acra"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-automated-imbalanced-learning-with","slug":"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","slug":"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","slug":"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","slug":"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":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/combinatorial-optimization-by-graph-pointer#ran","syntology_url":"https://syntology.ai/paper/1911.04936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04936"}},"official":{"repos":["qiang-ma/graph-pointer-network"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/learning-fairness-in-multi-agent-systems","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/from-debate-to-equilibrium-belief-driven#ran","syntology_url":"https://syntology.ai/paper/2506.08292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08292"}},"official":{"repos":["tmlr-group/econ"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/divide-and-conquer-grounding-llms-as","slug":"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","slug":"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":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/implicitly-aligning-humans-and-autonomous#ran","syntology_url":"https://syntology.ai/paper/2505.04579","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.04579"}},"official":{"repos":["HIRO-group/HA2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/solving-sokoban-using-hierarchical-1","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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},{"url":"/paper/2408-01880","slug":"2408-01880","title":"Walk Wisely on Graph: Knowledge Graph Reasoning with Dual Agents via Efficient Guidance-Exploration","date":"2024-08-03","arxiv_id":"2408.01880","repositories_listed":1,"syntology":null},{"url":"/paper/bio-silicon-intelligence-system-integrating","slug":"bio-silicon-intelligence-system-integrating","title":"AI-Driven Physics-Informed Bio-Silicon Intelligence System: Integrating Hybrid Systems, Biocomputing, Neural Networks, and Machine Learning, for Advanced Neurotechnology","date":"2024-07-12","arxiv_id":"2407.11939","repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-reachable-hierarchical","slug":"bidirectional-reachable-hierarchical","title":"Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies","date":"2024-06-26","arxiv_id":"2406.18053","repositories_listed":1,"syntology":null},{"url":"/paper/spatial-temporal-hierarchical-reinforcement","slug":"spatial-temporal-hierarchical-reinforcement","title":"Spatial-temporal Hierarchical Reinforcement Learning for Interpretable Pathology Image Super-Resolution","date":"2024-06-26","arxiv_id":"2406.18310","repositories_listed":1,"syntology":null},{"url":"/paper/kehrl-learning-knowledge-enhanced-language","slug":"kehrl-learning-knowledge-enhanced-language","title":"KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learning","date":"2024-06-24","arxiv_id":"2406.16374","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-subgoal-representations-for","slug":"probabilistic-subgoal-representations-for","title":"Probabilistic Subgoal Representations for Hierarchical Reinforcement learning","date":"2024-06-24","arxiv_id":"2406.16707","repositories_listed":1,"syntology":null},{"url":"/paper/macrohft-memory-augmented-context-aware","slug":"macrohft-memory-augmented-context-aware","title":"MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading","date":"2024-06-20","arxiv_id":"2406.14537","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":3,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/macrohft-memory-augmented-context-aware#ran","syntology_url":"https://syntology.ai/paper/2406.14537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14537"}},"official":{"repos":["ZONG0004/MacroHFT"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-reinforcement-learning-for-swarm","slug":"hierarchical-reinforcement-learning-for-swarm","title":"Hierarchical Reinforcement Learning for Swarm Confrontation with High Uncertainty","date":"2024-06-12","arxiv_id":"2406.07877","repositories_listed":1,"syntology":null},{"url":"/paper/piper-primitive-informed-preference-based","slug":"piper-primitive-informed-preference-based","title":"PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling","date":"2024-04-20","arxiv_id":"2404.13423","repositories_listed":1,"syntology":null},{"url":"/paper/mentor-guiding-hierarchical-reinforcement","slug":"mentor-guiding-hierarchical-reinforcement","title":"MENTOR: Guiding Hierarchical Reinforcement Learning with Human Feedback and Dynamic Distance Constraint","date":"2024-02-22","arxiv_id":"2402.14244","repositories_listed":1,"syntology":null},{"url":"/paper/reconciling-spatial-and-temporal-abstractions","slug":"reconciling-spatial-and-temporal-abstractions","title":"Reconciling Spatial and Temporal Abstractions for Goal Representation","date":"2024-01-18","arxiv_id":"2401.09870","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":11,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/reconciling-spatial-and-temporal-abstractions#ran","syntology_url":"https://syntology.ai/paper/2401.09870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09870"}},"official":{"repos":["cosynus-lix/STAR"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-reinforcement-learning-for-power","slug":"hierarchical-reinforcement-learning-for-power","title":"Hierarchical Reinforcement Learning for Power Network Topology Control","date":"2023-11-03","arxiv_id":"2311.02129","repositories_listed":1,"syntology":null},{"url":"/paper/chain-of-choice-hierarchical-policy-learning","slug":"chain-of-choice-hierarchical-policy-learning","title":"Chain-of-Choice Hierarchical Policy Learning for Conversational Recommendation","date":"2023-10-27","arxiv_id":"2310.17922","repositories_listed":1,"syntology":null},{"url":"/paper/feature-cognition-enhancement-via-interaction","slug":"feature-cognition-enhancement-via-interaction","title":"Feature Interaction Aware Automated Data Representation Transformation","date":"2023-09-29","arxiv_id":"2309.17011","repositories_listed":1,"syntology":null},{"url":"/paper/guided-cooperation-in-hierarchical","slug":"guided-cooperation-in-hierarchical","title":"Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout","date":"2023-09-24","arxiv_id":"2309.13508","repositories_listed":1,"syntology":null},{"url":"/paper/earnhft-efficient-hierarchical-reinforcement","slug":"earnhft-efficient-hierarchical-reinforcement","title":"EarnHFT: Efficient Hierarchical Reinforcement Learning for High Frequency Trading","date":"2023-09-22","arxiv_id":"2309.12891","repositories_listed":1,"syntology":null},{"url":"/paper/balancing-exploration-and-exploitation-in","slug":"balancing-exploration-and-exploitation-in","title":"Balancing Exploration and Exploitation in Hierarchical Reinforcement Learning via Latent Landmark Graphs","date":"2023-07-22","arxiv_id":"2307.12063","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/balancing-exploration-and-exploitation-in#ran","syntology_url":"https://syntology.ai/paper/2307.12063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12063"}},"official":{"repos":["papercode2022/hill"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/controllable-motion-diffusion-model","slug":"controllable-motion-diffusion-model","title":"Interactive Character Control with Auto-Regressive Motion Diffusion Models","date":"2023-06-01","arxiv_id":"2306.00416","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/controllable-motion-diffusion-model#ran","syntology_url":"https://syntology.ai/paper/2306.00416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00416"}},"official":{"repos":["Yi-Shi94/AMDM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dhrl-fnmr-an-intelligent-multicast-routing","slug":"dhrl-fnmr-an-intelligent-multicast-routing","title":"DHRL-FNMR: An Intelligent Multicast Routing Approach Based on Deep Hierarchical Reinforcement Learning in SDN","date":"2023-05-30","arxiv_id":"2305.19077","repositories_listed":1,"syntology":null},{"url":"/paper/a-hierarchical-approach-to-population","slug":"a-hierarchical-approach-to-population","title":"A Hierarchical Approach to Population Training for Human-AI Collaboration","date":"2023-05-26","arxiv_id":"2305.16708","repositories_listed":1,"syntology":null},{"url":"/paper/h-tsp-hierarchically-solving-the-large-scale","slug":"h-tsp-hierarchically-solving-the-large-scale","title":"H-TSP: Hierarchically Solving the Large-Scale Travelling Salesman Problem","date":"2023-04-19","arxiv_id":"2304.09395","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/h-tsp-hierarchically-solving-the-large-scale#ran","syntology_url":"https://syntology.ai/paper/2304.09395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09395"}},"official":{"repos":["Learning4Optimization-HUST/H-TSP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-graph-enhanced-commander-executor","slug":"learning-graph-enhanced-commander-executor","title":"Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation","date":"2023-02-08","arxiv_id":"2302.04094","repositories_listed":1,"syntology":null},{"url":"/paper/select-and-trade-towards-unified-pair-trading","slug":"select-and-trade-towards-unified-pair-trading","title":"Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement Learning","date":"2023-01-25","arxiv_id":"2301.10724","repositories_listed":1,"syntology":null},{"url":"/paper/meteor-guided-divergence-for-video-captioning","slug":"meteor-guided-divergence-for-video-captioning","title":"METEOR Guided Divergence for Video Captioning","date":"2022-12-20","arxiv_id":"2212.10690","repositories_listed":1,"syntology":null},{"url":"/paper/dhrl-a-graph-based-approach-for-long-horizon","slug":"dhrl-a-graph-based-approach-for-long-horizon","title":"DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning","date":"2022-10-11","arxiv_id":"2210.05150","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dhrl-a-graph-based-approach-for-long-horizon#ran","syntology_url":"https://syntology.ai/paper/2210.05150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05150"}},"official":null}},{"url":"/paper/from-scratch-to-sketch-deep-decoupled","slug":"from-scratch-to-sketch-deep-decoupled","title":"From Scratch to Sketch: Deep Decoupled Hierarchical Reinforcement Learning for Robotic Sketching Agent","date":"2022-08-09","arxiv_id":"2208.04833","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-enhanced-shared","slug":"reinforcement-learning-enhanced-shared","title":"Reinforcement Learning-enhanced Shared-account Cross-domain Sequential Recommendation","date":"2022-06-16","arxiv_id":"2206.08088","repositories_listed":1,"syntology":null},{"url":"/paper/deep-hierarchical-planning-from-pixels","slug":"deep-hierarchical-planning-from-pixels","title":"Deep Hierarchical Planning from Pixels","date":"2022-06-08","arxiv_id":"2206.04114","repositories_listed":1,"syntology":null},{"url":"/paper/possibility-before-utility-learning-and-using-1","slug":"possibility-before-utility-learning-and-using-1","title":"Possibility Before Utility: Learning And Using Hierarchical Affordances","date":"2022-03-23","arxiv_id":"2203.12686","repositories_listed":1,"syntology":null},{"url":"/paper/on-credit-assignment-in-hierarchical","slug":"on-credit-assignment-in-hierarchical","title":"On Credit Assignment in Hierarchical Reinforcement Learning","date":"2022-03-07","arxiv_id":"2203.03292","repositories_listed":1,"syntology":null},{"url":"/paper/ai-planning-annotation-for-sample-efficient","slug":"ai-planning-annotation-for-sample-efficient","title":"Hierarchical Reinforcement Learning with AI Planning Models","date":"2022-03-01","arxiv_id":"2203.00669","repositories_listed":1,"syntology":null},{"url":"/paper/the-paradox-of-choice-using-attention-in","slug":"the-paradox-of-choice-using-attention-in","title":"The Paradox of Choice: Using Attention in Hierarchical Reinforcement Learning","date":"2022-01-24","arxiv_id":"2201.09653","repositories_listed":1,"syntology":null},{"url":"/paper/learning-multiple-gaits-of-quadruped-robot","slug":"learning-multiple-gaits-of-quadruped-robot","title":"Learning multiple gaits of quadruped robot using hierarchical reinforcement learning","date":"2021-12-09","arxiv_id":"2112.04741","repositories_listed":1,"syntology":null},{"url":"/paper/flexible-option-learning-1","slug":"flexible-option-learning-1","title":"Flexible Option Learning","date":"2021-12-06","arxiv_id":"2112.03097","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-reinforcement-learning-with-5","slug":"hierarchical-reinforcement-learning-with-5","title":"Hierarchical Reinforcement Learning with Timed Subgoals","date":"2021-12-06","arxiv_id":"2112.03100","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/hierarchical-reinforcement-learning-with-5#ran","syntology_url":"https://syntology.ai/paper/2112.03100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03100"}},"official":{"repos":["martius-lab/hits"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/landmark-guided-subgoal-generation-in","slug":"landmark-guided-subgoal-generation-in","title":"Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning","date":"2021-10-26","arxiv_id":"2110.13625","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/landmark-guided-subgoal-generation-in#ran","syntology_url":"https://syntology.ai/paper/2110.13625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13625"}},"official":{"repos":["junsu-kim97/higl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-skills-for-efficient-exploration","slug":"hierarchical-skills-for-efficient-exploration","title":"Hierarchical Skills for Efficient Exploration","date":"2021-10-20","arxiv_id":"2110.10809","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hierarchical-skills-for-efficient-exploration#ran","syntology_url":"https://syntology.ai/paper/2110.10809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.10809"}},"official":{"repos":["facebookresearch/hsd3"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/training-transition-policies-via-distribution-1","slug":"training-transition-policies-via-distribution-1","title":"Training Transition Policies via Distribution Matching for Complex Tasks","date":"2021-10-08","arxiv_id":"2110.04357","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-in-text-based-games-via","slug":"generalization-in-text-based-games-via","title":"Generalization in Text-based Games via Hierarchical Reinforcement Learning","date":"2021-09-21","arxiv_id":"2109.09968","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalization-in-text-based-games-via#ran","syntology_url":"https://syntology.ai/paper/2109.09968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.09968"}},"official":{"repos":["yunqiuxu/h-kga"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/context-specific-representation-abstraction","slug":"context-specific-representation-abstraction","title":"Context-Specific Representation Abstraction for Deep Option Learning","date":"2021-09-20","arxiv_id":"2109.09876","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-reinforcement-learning-with-2","slug":"hierarchical-reinforcement-learning-with-2","title":"Hierarchical Reinforcement Learning with Optimal Level Synchronization based on a Deep Generative Model","date":"2021-07-17","arxiv_id":"2107.08183","repositories_listed":1,"syntology":null},{"url":"/paper/computational-benefits-of-intermediate","slug":"computational-benefits-of-intermediate","title":"Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning","date":"2021-07-08","arxiv_id":"2107.03961","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/computational-benefits-of-intermediate#ran","syntology_url":"https://syntology.ai/paper/2107.03961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.03961"}},"official":{"repos":["kebaek/minigrid"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/globally-optimal-hierarchical-reinforcement","slug":"globally-optimal-hierarchical-reinforcement","title":"Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes","date":"2021-06-29","arxiv_id":"2106.15380","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-hierarchical-exploration-with","slug":"efficient-hierarchical-exploration-with","title":"Active Hierarchical Exploration with Stable Subgoal Representation Learning","date":"2021-05-31","arxiv_id":"2105.14750","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/efficient-hierarchical-exploration-with#ran","syntology_url":"https://syntology.ai/paper/2105.14750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14750"}},"official":{"repos":["siyuanlee/hess"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/hierarchical-and-partially-observable-goal","slug":"hierarchical-and-partially-observable-goal","title":"Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph","date":"2021-03-01","arxiv_id":"2103.01350","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/hierarchical-and-partially-observable-goal#ran","syntology_url":"https://syntology.ai/paper/2103.01350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01350"}},"official":{"repos":["Xin-Ye-1/HRL-GRG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/intrinsically-motivated-open-ended-multi-task","slug":"intrinsically-motivated-open-ended-multi-task","title":"Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy","date":"2021-02-19","arxiv_id":"2102.09854","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-reinforcement-learning-by-1","slug":"hierarchical-reinforcement-learning-by-1","title":"Hierarchical Reinforcement Learning By Discovering Intrinsic Options","date":"2021-01-16","arxiv_id":"2101.06521","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-meta-reinforcement-learning-for","slug":"hierarchical-meta-reinforcement-learning-for","title":"Hierarchical Meta Reinforcement Learning for Multi-Task Environments","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/trajectory-planning-for-autonomous-vehicles","slug":"trajectory-planning-for-autonomous-vehicles","title":"Trajectory Planning for Autonomous Vehicles Using Hierarchical Reinforcement Learning","date":"2020-11-09","arxiv_id":"2011.04752","repositories_listed":1,"syntology":null},{"url":"/paper/provable-hierarchical-imitation-learning-via","slug":"provable-hierarchical-imitation-learning-via","title":"Provable Hierarchical Imitation Learning via EM","date":"2020-10-07","arxiv_id":"2010.03133","repositories_listed":1,"syntology":null},{"url":"/paper/learning-event-triggered-control-from-data","slug":"learning-event-triggered-control-from-data","title":"Learning Event-triggered Control from Data through Joint Optimization","date":"2020-08-11","arxiv_id":"2008.04712","repositories_listed":1,"syntology":null},{"url":"/paper/generating-adjacency-constrained-subgoals-in","slug":"generating-adjacency-constrained-subgoals-in","title":"Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning","date":"2020-06-20","arxiv_id":"2006.11485","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generating-adjacency-constrained-subgoals-in#ran","syntology_url":"https://syntology.ai/paper/2006.11485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11485"}},"official":{"repos":["trzhang0116/HRAC"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/compositional-generalization-by-learning","slug":"compositional-generalization-by-learning","title":"Compositional Generalization by Learning Analytical Expressions","date":"2020-06-18","arxiv_id":"2006.10627","repositories_listed":1,"syntology":null},{"url":"/paper/forgetful-experience-replay-in-hierarchical","slug":"forgetful-experience-replay-in-hierarchical","title":"Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations","date":"2020-06-17","arxiv_id":"2006.09939","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-for-multi-product","slug":"reinforcement-learning-for-multi-product","title":"Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains","date":"2020-06-07","arxiv_id":"2006.04037","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reinforcement-learning-for-multi-product#ran","syntology_url":"https://syntology.ai/paper/2006.04037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04037"}},"official":null}},{"url":"/paper/curious-hierarchical-actor-critic","slug":"curious-hierarchical-actor-critic","title":"Curious Hierarchical Actor-Critic Reinforcement Learning","date":"2020-05-07","arxiv_id":"2005.03420","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/curious-hierarchical-actor-critic#ran","syntology_url":"https://syntology.ai/paper/2005.03420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.03420"}},"official":{"repos":["knowledgetechnologyuhh/goal_conditioned_RL_baselines"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/option-discovery-using-deep-skill-chaining","slug":"option-discovery-using-deep-skill-chaining","title":"Option Discovery using Deep Skill Chaining","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/combined-model-for-partially-observable-and-1","slug":"combined-model-for-partially-observable-and-1","title":"Combined Model for Partially-Observable and Non-Observable Task Switching: Solving Hierarchical Reinforcement Learning Problems Statically and Dynamically with Transfer Learning","date":"2020-04-13","arxiv_id":"2004.06213","repositories_listed":1,"syntology":null},{"url":"/paper/191202368","slug":"191202368","title":"Inter-Level Cooperation in Hierarchical Reinforcement Learning","date":"2019-12-05","arxiv_id":"1912.02368","repositories_listed":1,"syntology":null},{"url":"/paper/combined-model-for-partially-observable-and","slug":"combined-model-for-partially-observable-and","title":"Combined Model for Partially-Observable and Non-Observable Task Switching: Solving Hierarchical Reinforcement Learning Problems Statically and Dynamically with Transfer Learning","date":"2019-11-23","arxiv_id":"1911.10425","repositories_listed":1,"syntology":null},{"url":"/paper/deepsynth-program-synthesis-for-automatic","slug":"deepsynth-program-synthesis-for-automatic","title":"DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning","date":"2019-11-22","arxiv_id":"1911.10244","repositories_listed":1,"syntology":null},{"url":"/paper/hrl4in-hierarchical-reinforcement-learning","slug":"hrl4in-hierarchical-reinforcement-learning","title":"HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulators","date":"2019-10-24","arxiv_id":"1910.11432","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hrl4in-hierarchical-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1910.11432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.11432"}},"official":null}},{"url":"/paper/hierarchical-reinforcement-learning-with-3","slug":"hierarchical-reinforcement-learning-with-3","title":"Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards","date":"2019-10-10","arxiv_id":"1910.04450","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-reinforcement-learning-for-open","slug":"hierarchical-reinforcement-learning-for-open","title":"Hierarchical Reinforcement Learning for Open-Domain Dialog","date":"2019-09-17","arxiv_id":"1909.07547","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-for-temporal-logic","slug":"reinforcement-learning-for-temporal-logic","title":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees","date":"2019-09-11","arxiv_id":"1909.05304","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-for-temporal-logic#ran","syntology_url":"https://syntology.ai/paper/1909.05304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05304"}},"official":{"repos":["grockious/lcrl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/action-grammars-a-cognitive-model-for","slug":"action-grammars-a-cognitive-model-for","title":"Semantic RL with Action Grammars: Data-Efficient Learning of Hierarchical Task Abstractions","date":"2019-07-29","arxiv_id":"1907.12477","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-reinforcement-learning-for-1","slug":"hierarchical-reinforcement-learning-for-1","title":"Hierarchical Reinforcement Learning for Concurrent Discovery of Compound and Composable Policies","date":"2019-05-23","arxiv_id":"1905.09668","repositories_listed":1,"syntology":null},{"url":"/paper/model-primitive-hierarchical-lifelong","slug":"model-primitive-hierarchical-lifelong","title":"Model Primitive Hierarchical Lifelong Reinforcement Learning","date":"2019-03-04","arxiv_id":"1903.01567","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-primitive-hierarchical-lifelong#ran","syntology_url":"https://syntology.ai/paper/1903.01567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.01567"}},"official":{"repos":["sisl/MPHRL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/certified-reinforcement-learning-with-logic","slug":"certified-reinforcement-learning-with-logic","title":"Certified Reinforcement Learning with Logic Guidance","date":"2019-02-02","arxiv_id":"1902.00778","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-reinforcement-learning-via","slug":"hierarchical-reinforcement-learning-via","title":"Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization","date":"2019-01-05","arxiv_id":"1901.01365","repositories_listed":1,"syntology":null}],"syntology_records":24,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":22,"papers_where_code_ran_first_page":"/task/hierarchical-reinforcement-learning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/hierarchical-reinforcement-learning/papers/2","json":"/task/hierarchical-reinforcement-learning/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/hierarchical-reinforcement-learning/papers/3","json":"/task/hierarchical-reinforcement-learning/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/hierarchical-reinforcement-learning/papers/4","json":"/task/hierarchical-reinforcement-learning/papers/4.json","rows":84},{"order":"ran","page":1,"of":1,"url":"/task/hierarchical-reinforcement-learning/papers/ran/1","json":"/task/hierarchical-reinforcement-learning/papers/ran/1.json","rows":22}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"a9212f397795b449188bc175f9029543dff7eadb3779670e78349366e8d6c382","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}