{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:Y5USRNFY3GCBU2YSRTE5POQ76T","short_pith_number":"pith:Y5USRNFY","schema_version":"1.0","canonical_sha256":"c76928b4b8d9841a6b128cc9d7ba1ff4f1a9f873f23e6fd857d878ec9e25fad8","source":{"kind":"arxiv","id":"1301.7381","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Solution of Markov Decision Processes using Macro-actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Craig Boutilier, Leslie Pack Kaelbling, Milos Hauskrecht, Nicolas Meuleau, Thomas L. Dean","submitted_at":"2013-01-30T15:04:16Z","abstract_excerpt":"We investigate the use of temporally abstract actions, or macro-actions, in the solution of Markov decision processes. Unlike current models that combine both primitive actions and macro-actions and leave the state space unchanged, we propose a hierarchical model (using an abstract MDP) that works with macro-actions only, and that significantly reduces the size of the state space. This is achieved by treating macroactions as local policies that act in certain regions of state space, and by restricting states in the abstract MDP to those at the boundaries of regions. The abstract MDP approximat"},"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":"1301.7381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-30T15:04:16Z","cross_cats_sorted":[],"title_canon_sha256":"542a89705f047a2263c5df020d33482dfc53dad8afd3491c380e9ea65293114d","abstract_canon_sha256":"0f9a2a5411c4b2a7b9a497afe1a4ccefb6cf35797b51cb3c16b9d78e1b042f22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:35:00.162386Z","signature_b64":"OnF9YtA6yyN3Lq23Q1WHC6RKYSdbohEjuT3WMIbjBBNGOtahPnx6rajHbQ3HLo8fu5P8bkCsNQbKpfwT5i9OCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c76928b4b8d9841a6b128cc9d7ba1ff4f1a9f873f23e6fd857d878ec9e25fad8","last_reissued_at":"2026-05-18T03:35:00.161427Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:35:00.161427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Solution of Markov Decision Processes using Macro-actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Craig Boutilier, Leslie Pack Kaelbling, Milos Hauskrecht, Nicolas Meuleau, Thomas L. Dean","submitted_at":"2013-01-30T15:04:16Z","abstract_excerpt":"We investigate the use of temporally abstract actions, or macro-actions, in the solution of Markov decision processes. Unlike current models that combine both primitive actions and macro-actions and leave the state space unchanged, we propose a hierarchical model (using an abstract MDP) that works with macro-actions only, and that significantly reduces the size of the state space. This is achieved by treating macroactions as local policies that act in certain regions of state space, and by restricting states in the abstract MDP to those at the boundaries of regions. The abstract MDP approximat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.7381","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":""},"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":"1301.7381","created_at":"2026-05-18T03:35:00.161576+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.7381v1","created_at":"2026-05-18T03:35:00.161576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.7381","created_at":"2026-05-18T03:35:00.161576+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5USRNFY3GCB","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5USRNFY3GCBU2YS","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5USRNFY","created_at":"2026-05-18T12:28:06.772260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.09860","citing_title":"When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09860","citing_title":"When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09860","citing_title":"When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y5USRNFY3GCBU2YSRTE5POQ76T","json":"https://pith.science/pith/Y5USRNFY3GCBU2YSRTE5POQ76T.json","graph_json":"https://pith.science/api/pith-number/Y5USRNFY3GCBU2YSRTE5POQ76T/graph.json","events_json":"https://pith.science/api/pith-number/Y5USRNFY3GCBU2YSRTE5POQ76T/events.json","paper":"https://pith.science/paper/Y5USRNFY"},"agent_actions":{"view_html":"https://pith.science/pith/Y5USRNFY3GCBU2YSRTE5POQ76T","download_json":"https://pith.science/pith/Y5USRNFY3GCBU2YSRTE5POQ76T.json","view_paper":"https://pith.science/paper/Y5USRNFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.7381&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5USRNFY3GCBU2YSRTE5POQ76T/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5USRNFY3GCBU2YSRTE5POQ76T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5USRNFY3GCBU2YSRTE5POQ76T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5USRNFY3GCBU2YSRTE5POQ76T/action/storage_attestation","attest_author":"https://pith.science/pith/Y5USRNFY3GCBU2YSRTE5POQ76T/action/author_attestation","sign_citation":"https://pith.science/pith/Y5USRNFY3GCBU2YSRTE5POQ76T/action/citation_signature","submit_replication":"https://pith.science/pith/Y5USRNFY3GCBU2YSRTE5POQ76T/action/replication_record"}},"created_at":"2026-05-18T03:35:00.161576+00:00","updated_at":"2026-05-18T03:35:00.161576+00:00"}