{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TBOBY5MEY2RAQYD6VHKX7GXO3D","short_pith_number":"pith:TBOBY5ME","schema_version":"1.0","canonical_sha256":"985c1c7584c6a208607ea9d57f9aeed8ec787a182207e4d7efef9984f700617f","source":{"kind":"arxiv","id":"1804.07779","version":3},"attestation_state":"computed","paper":{"title":"PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Daoming Lyu, Fangkai Yang, Steven Gustafson","submitted_at":"2018-04-20T18:16:43Z","abstract_excerpt":"Reinforcement learning and symbolic planning have both been used to build intelligent autonomous agents. Reinforcement learning relies on learning from interactions with real world, which often requires an unfeasibly large amount of experience. Symbolic planning relies on manually crafted symbolic knowledge, which may not be robust to domain uncertainties and changes. In this paper we present a unified framework {\\em PEORL} that integrates symbolic planning with hierarchical reinforcement learning (HRL) to cope with decision-making in a dynamic environment with uncertainties.\n  Symbolic plans "},"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":"1804.07779","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-20T18:16:43Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"17c363b907a55cf981857900f76ac19fc2e67c443aacc4d970efcfbd85994d36","abstract_canon_sha256":"3413c7ab54bed111053a4f82a1ee81094fb17024635d62852b9bc17a23b9a9bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:06.105659Z","signature_b64":"1JQjM5jSa2WVD4NgmADYkoLUeLcu0cqQ6K3aWH/3mTS1sltASuahxiOvyOdyeVBrzQ/m5iC6MoFmJkdL11LXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"985c1c7584c6a208607ea9d57f9aeed8ec787a182207e4d7efef9984f700617f","last_reissued_at":"2026-05-18T00:14:06.104959Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:06.104959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Daoming Lyu, Fangkai Yang, Steven Gustafson","submitted_at":"2018-04-20T18:16:43Z","abstract_excerpt":"Reinforcement learning and symbolic planning have both been used to build intelligent autonomous agents. Reinforcement learning relies on learning from interactions with real world, which often requires an unfeasibly large amount of experience. Symbolic planning relies on manually crafted symbolic knowledge, which may not be robust to domain uncertainties and changes. In this paper we present a unified framework {\\em PEORL} that integrates symbolic planning with hierarchical reinforcement learning (HRL) to cope with decision-making in a dynamic environment with uncertainties.\n  Symbolic plans "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07779","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1804.07779","created_at":"2026-05-18T00:14:06.105079+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.07779v3","created_at":"2026-05-18T00:14:06.105079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07779","created_at":"2026-05-18T00:14:06.105079+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBOBY5MEY2RA","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBOBY5MEY2RAQYD6","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBOBY5ME","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2604.28087","citing_title":"Towards Neuro-symbolic Causal Rule Synthesis, Verification, and Evaluation Grounded in Legal and Safety Principles","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28087","citing_title":"Towards Neuro-symbolic Causal Rule Synthesis, Verification, and Evaluation Grounded in Legal and Safety Principles","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBOBY5MEY2RAQYD6VHKX7GXO3D","json":"https://pith.science/pith/TBOBY5MEY2RAQYD6VHKX7GXO3D.json","graph_json":"https://pith.science/api/pith-number/TBOBY5MEY2RAQYD6VHKX7GXO3D/graph.json","events_json":"https://pith.science/api/pith-number/TBOBY5MEY2RAQYD6VHKX7GXO3D/events.json","paper":"https://pith.science/paper/TBOBY5ME"},"agent_actions":{"view_html":"https://pith.science/pith/TBOBY5MEY2RAQYD6VHKX7GXO3D","download_json":"https://pith.science/pith/TBOBY5MEY2RAQYD6VHKX7GXO3D.json","view_paper":"https://pith.science/paper/TBOBY5ME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.07779&json=true","fetch_graph":"https://pith.science/api/pith-number/TBOBY5MEY2RAQYD6VHKX7GXO3D/graph.json","fetch_events":"https://pith.science/api/pith-number/TBOBY5MEY2RAQYD6VHKX7GXO3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBOBY5MEY2RAQYD6VHKX7GXO3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBOBY5MEY2RAQYD6VHKX7GXO3D/action/storage_attestation","attest_author":"https://pith.science/pith/TBOBY5MEY2RAQYD6VHKX7GXO3D/action/author_attestation","sign_citation":"https://pith.science/pith/TBOBY5MEY2RAQYD6VHKX7GXO3D/action/citation_signature","submit_replication":"https://pith.science/pith/TBOBY5MEY2RAQYD6VHKX7GXO3D/action/replication_record"}},"created_at":"2026-05-18T00:14:06.105079+00:00","updated_at":"2026-05-18T00:14:06.105079+00:00"}