{"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/go-for-a-walk-and-arrive-at-the-answer","title":"Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning","arxiv_id":"1711.05851","date":"2017-11-15","proceeding":"ICLR 2018 1","authors":["Rajarshi Das","Shehzaad Dhuliawala","Manzil Zaheer","Luke Vilnis","Ishan Durugkar","Akshay Krishnamurthy","Alex Smola","Andrew McCallum"],"abstract":"Knowledge bases (KB), both automatically and manually constructed, are often\nincomplete --- many valid facts can be inferred from the KB by synthesizing\nexisting information. A popular approach to KB completion is to infer new\nrelations by combinatory reasoning over the information found along other paths\nconnecting a pair of entities. Given the enormous size of KBs and the\nexponential number of paths, previous path-based models have considered only\nthe problem of predicting a missing relation given two entities or evaluating\nthe truth of a proposed triple. Additionally, these methods have traditionally\nused random paths between fixed entity pairs or more recently learned to pick\npaths between them. We propose a new algorithm MINERVA, which addresses the\nmuch more difficult and practical task of answering questions where the\nrelation is known, but only one entity. Since random walks are impractical in a\nsetting with combinatorially many destinations from a start node, we present a\nneural reinforcement learning approach which learns how to navigate the graph\nconditioned on the input query to find predictive paths. Empirically, this\napproach obtains state-of-the-art results on several datasets, significantly\noutperforming prior methods.","url_abs":"http://arxiv.org/abs/1711.05851v2","url_pdf":"http://arxiv.org/pdf/1711.05851v2.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":"go-for-a-walk-and-arrive-at-the-answer","repo_url":"https://github.com/shehzaadzd/MINERVA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"go-for-a-walk-and-arrive-at-the-answer","repo_url":"https://github.com/JohnKurian/R2D2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"go-for-a-walk-and-arrive-at-the-answer","repo_url":"https://github.com/laurendelong21/mars","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"go-for-a-walk-and-arrive-at-the-answer","repo_url":"https://github.com/liu-yushan/PoLo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"go-for-a-walk-and-arrive-at-the-answer","repo_url":"https://github.com/m-hildebrandt/R2D2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"go-for-a-walk-and-arrive-at-the-answer","repo_url":"https://github.com/marina-sp/reinform","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"go-for-a-walk-and-arrive-at-the-answer","repo_url":"https://github.com/markWJJ/rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"go-for-a-walk-and-arrive-at-the-answer","repo_url":"https://github.com/ty4b112/pytorch_MINERVA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":null,"task_name":"Relation"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.05851","atlas_url":"https://app.syntology.ai/?focus=1711.05851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.05851"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liu-yushan/PoLo","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shehzaadzd/MINERVA","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/m-hildebrandt/R2D2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JohnKurian/R2D2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/markWJJ/rl","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ty4b112/pytorch_MINERVA","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marina-sp/reinform","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/laurendelong21/mars","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"listed":{"samples":8,"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":"ce7c9ee686c9c031","entry":"check_rule","repo":"liu-yushan/PoLo","repo_kind":"listed","path":"mycode/model/rules.py","file_url":"https://github.com/liu-yushan/PoLo/blob/HEAD/mycode/model/rules.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ce7c9ee686c9c031"}},{"code_sha256_prefix":"49ae84b4e9adad02","entry":"create_output_and_model_dir","repo":"liu-yushan/PoLo","repo_kind":"listed","path":"mycode/model/trainer.py","file_url":"https://github.com/liu-yushan/PoLo/blob/HEAD/mycode/model/trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"49ae84b4e9adad02"}},{"code_sha256_prefix":"235febb7d1bd55ef","entry":"get_conf_length_1","repo":"liu-yushan/PoLo","repo_kind":"listed","path":"datasets/Hetionet/preprocessing/calculate_confidence.py","file_url":"https://github.com/liu-yushan/PoLo/blob/HEAD/datasets/Hetionet/preprocessing/calculate_confidence.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"235febb7d1bd55ef"}},{"code_sha256_prefix":"26788190b1493200","entry":"get_conf_length_2","repo":"liu-yushan/PoLo","repo_kind":"listed","path":"datasets/Hetionet/preprocessing/calculate_confidence.py","file_url":"https://github.com/liu-yushan/PoLo/blob/HEAD/datasets/Hetionet/preprocessing/calculate_confidence.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"26788190b1493200"}},{"code_sha256_prefix":"776926e52bd63a83","entry":"get_conf_length_3","repo":"liu-yushan/PoLo","repo_kind":"listed","path":"datasets/Hetionet/preprocessing/calculate_confidence.py","file_url":"https://github.com/liu-yushan/PoLo/blob/HEAD/datasets/Hetionet/preprocessing/calculate_confidence.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"776926e52bd63a83"}},{"code_sha256_prefix":"ba8093f2012bdfe9","entry":"initialize_setting","repo":"liu-yushan/PoLo","repo_kind":"listed","path":"mycode/model/trainer.py","file_url":"https://github.com/liu-yushan/PoLo/blob/HEAD/mycode/model/trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ba8093f2012bdfe9"}},{"code_sha256_prefix":"32c81ffd6db50f7e","entry":"modify_rewards","repo":"liu-yushan/PoLo","repo_kind":"listed","path":"mycode/model/rules.py","file_url":"https://github.com/liu-yushan/PoLo/blob/HEAD/mycode/model/rules.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"32c81ffd6db50f7e"}},{"code_sha256_prefix":"1852640726232918","entry":"prepare_argument","repo":"liu-yushan/PoLo","repo_kind":"listed","path":"mycode/model/rules.py","file_url":"https://github.com/liu-yushan/PoLo/blob/HEAD/mycode/model/rules.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1852640726232918"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}