{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/graph-assisted-stitching-for-offline","title":"Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning","arxiv_id":"2506.07744","date":"2025-06-09","proceeding":null,"authors":["Seungho Baek","Taegeon Park","Jongchan Park","Seungjun Oh","Yusung Kim"],"abstract":"Existing offline hierarchical reinforcement learning methods rely on high-level policy learning to generate subgoal sequences. However, their efficiency degrades as task horizons increase, and they lack effective strategies for stitching useful state transitions across different trajectories. We propose Graph-Assisted Stitching (GAS), a novel framework that formulates subgoal selection as a graph search problem rather than learning an explicit high-level policy. By embedding states into a Temporal Distance Representation (TDR) space, GAS clusters semantically similar states from different trajectories into unified graph nodes, enabling efficient transition stitching. A shortest-path algorithm is then applied to select subgoal sequences within the graph, while a low-level policy learns to reach the subgoals. To improve graph quality, we introduce the Temporal Efficiency (TE) metric, which filters out noisy or inefficient transition states, significantly enhancing task performance. GAS outperforms prior offline HRL methods across locomotion, navigation, and manipulation tasks. Notably, in the most stitching-critical task, it achieves a score of 88.3, dramatically surpassing the previous state-of-the-art score of 1.0. Our source code is available at: https://github.com/qortmdgh4141/GAS.","url_abs":"https://arxiv.org/abs/2506.07744v2","url_pdf":"https://arxiv.org/pdf/2506.07744v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"graph-assisted-stitching-for-offline","repo_url":"https://github.com/qortmdgh4141/gas","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.07744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.07744"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/qortmdgh4141/GAS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qortmdgh4141/gas","reach":null}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c7b80579137cc466","entry":"GASAgent","repo":"qortmdgh4141/gas","repo_kind":"official","path":"M_utils/agents/gas.py","file_url":"https://github.com/qortmdgh4141/gas/blob/HEAD/M_utils/agents/gas.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c7b80579137cc466"}},{"code_sha256_prefix":"bdd840eb05072a5f","entry":"GCActor","repo":"qortmdgh4141/gas","repo_kind":"official","path":"M_utils/agents/gas.py","file_url":"https://github.com/qortmdgh4141/gas/blob/HEAD/M_utils/agents/gas.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdd840eb05072a5f"}},{"code_sha256_prefix":"a43fdd56c756deba","entry":"GCEncoder","repo":"qortmdgh4141/gas","repo_kind":"official","path":"M_utils/agents/gas.py","file_url":"https://github.com/qortmdgh4141/gas/blob/HEAD/M_utils/agents/gas.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a43fdd56c756deba"}},{"code_sha256_prefix":"555b3901a771182f","entry":"GCPhiValue","repo":"qortmdgh4141/gas","repo_kind":"official","path":"M_utils/agents/gas.py","file_url":"https://github.com/qortmdgh4141/gas/blob/HEAD/M_utils/agents/gas.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"555b3901a771182f"}},{"code_sha256_prefix":"bd4a5c069a890193","entry":"GCValue","repo":"qortmdgh4141/gas","repo_kind":"official","path":"M_utils/agents/gas.py","file_url":"https://github.com/qortmdgh4141/gas/blob/HEAD/M_utils/agents/gas.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd4a5c069a890193"}},{"code_sha256_prefix":"82782644cf3e631b","entry":"ImpalaEncoder","repo":"qortmdgh4141/gas","repo_kind":"official","path":"M_utils/agents/gas.py","file_url":"https://github.com/qortmdgh4141/gas/blob/HEAD/M_utils/agents/gas.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"82782644cf3e631b"}},{"code_sha256_prefix":"5ea4698a49c7d0bf","entry":"MLP","repo":"qortmdgh4141/gas","repo_kind":"official","path":"M_utils/agents/gas.py","file_url":"https://github.com/qortmdgh4141/gas/blob/HEAD/M_utils/agents/gas.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ea4698a49c7d0bf"}},{"code_sha256_prefix":"6ba4609bf30074d0","entry":"ModuleDict","repo":"qortmdgh4141/gas","repo_kind":"official","path":"M_utils/agents/gas.py","file_url":"https://github.com/qortmdgh4141/gas/blob/HEAD/M_utils/agents/gas.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ba4609bf30074d0"}},{"code_sha256_prefix":"7e48283b621200f7","entry":"TrainState","repo":"qortmdgh4141/gas","repo_kind":"official","path":"M_utils/agents/gas.py","file_url":"https://github.com/qortmdgh4141/gas/blob/HEAD/M_utils/agents/gas.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e48283b621200f7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}