{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UBGH4DG6IO2RWKQHG3SVKDENZX","short_pith_number":"pith:UBGH4DG6","schema_version":"1.0","canonical_sha256":"a04c7e0cde43b51b2a0736e5550c8dcddfbb653d2c1f6f8f319be980224ab8a5","source":{"kind":"arxiv","id":"2106.11417","version":1},"attestation_state":"computed","paper":{"title":"Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Duo Xu, Faramarz Fekri","submitted_at":"2021-06-21T21:30:08Z","abstract_excerpt":"Recently deep reinforcement learning has achieved tremendous success in wide ranges of applications. However, it notoriously lacks data-efficiency and interpretability. Data-efficiency is important as interacting with the environment is expensive. Further, interpretability can increase the transparency of the black-box-style deep RL models and hence gain trust from the users. In this work, we propose a new hierarchical framework via symbolic RL, leveraging a symbolic transition model to improve the data-efficiency and introduce the interpretability for learned policy. This framework consists o"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.11417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-21T21:30:08Z","cross_cats_sorted":[],"title_canon_sha256":"d81cfaac49e9d541c232070f6e9d0cbc5586ddf9fd08f8c69f9f5788f1abca32","abstract_canon_sha256":"33e64f577d7c32856fc7533646d499477be72caa515187e4c837a30a4621b0c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:29.083466Z","signature_b64":"u0fuww1d48Gx/1oQ65IHcUAxl3wXElcJib6mPaoAQmoqWIDHHM4MSk9yMjlXXdzJuEsgKi+FZprpl9rpmlOFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a04c7e0cde43b51b2a0736e5550c8dcddfbb653d2c1f6f8f319be980224ab8a5","last_reissued_at":"2026-07-05T02:51:29.083048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:29.083048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Duo Xu, Faramarz Fekri","submitted_at":"2021-06-21T21:30:08Z","abstract_excerpt":"Recently deep reinforcement learning has achieved tremendous success in wide ranges of applications. However, it notoriously lacks data-efficiency and interpretability. Data-efficiency is important as interacting with the environment is expensive. Further, interpretability can increase the transparency of the black-box-style deep RL models and hence gain trust from the users. In this work, we propose a new hierarchical framework via symbolic RL, leveraging a symbolic transition model to improve the data-efficiency and introduce the interpretability for learned policy. This framework consists o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11417","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.11417/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.11417","created_at":"2026-07-05T02:51:29.083104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.11417v1","created_at":"2026-07-05T02:51:29.083104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11417","created_at":"2026-07-05T02:51:29.083104+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBGH4DG6IO2R","created_at":"2026-07-05T02:51:29.083104+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBGH4DG6IO2RWKQH","created_at":"2026-07-05T02:51:29.083104+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBGH4DG6","created_at":"2026-07-05T02:51:29.083104+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09417","citing_title":"A Survey of Reinforcement Learning for Optimization in Automation","ref_index":89,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX","json":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX.json","graph_json":"https://pith.science/api/pith-number/UBGH4DG6IO2RWKQHG3SVKDENZX/graph.json","events_json":"https://pith.science/api/pith-number/UBGH4DG6IO2RWKQHG3SVKDENZX/events.json","paper":"https://pith.science/paper/UBGH4DG6"},"agent_actions":{"view_html":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX","download_json":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX.json","view_paper":"https://pith.science/paper/UBGH4DG6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.11417&json=true","fetch_graph":"https://pith.science/api/pith-number/UBGH4DG6IO2RWKQHG3SVKDENZX/graph.json","fetch_events":"https://pith.science/api/pith-number/UBGH4DG6IO2RWKQHG3SVKDENZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX/action/storage_attestation","attest_author":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX/action/author_attestation","sign_citation":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX/action/citation_signature","submit_replication":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX/action/replication_record"}},"created_at":"2026-07-05T02:51:29.083104+00:00","updated_at":"2026-07-05T02:51:29.083104+00:00"}