{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IV56GWTDIKGDNSYYBILFTFUIEX","short_pith_number":"pith:IV56GWTD","schema_version":"1.0","canonical_sha256":"457be35a63428c36cb180a1659968825c80c2483c3f5dc411052e2b1c746863d","source":{"kind":"arxiv","id":"1901.11524","version":3},"attestation_state":"computed","paper":{"title":"The Value Function Polytope in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrien Ali Ta\\\"iga, Dale Schuurmans, Marc G. Bellemare, Nicolas Le Roux, Robert Dadashi","submitted_at":"2019-01-31T18:45:04Z","abstract_excerpt":"We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main contribution is the characterization of the nature of its shape: a general polytope (Aigner et al., 2010). To demonstrate this result, we exhibit several properties of the structural relationship between policies and value functions including the line theorem, which shows that the value functions of policies constrained on all but one state describe a line segment. Finally, we use this novel perspective to introduce visualizations to enhance the understan"},"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":"1901.11524","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T18:45:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a7a70255797a32133aff449e5a1b9e1869c1bea35d20f3df585e18ada1727f70","abstract_canon_sha256":"ab9113f38dab00c7b58ebaaf5cbb3fe1ccd5be2cea2d4da5ff089bbcfb5e395e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:03.576030Z","signature_b64":"Rc0YzxjFBLoC5Sm5iZG2kdMC0jq8acWJthTD6c1yPhFWhvaMXVGw5TxBZgA5DUoIA4G+cAzsxZF9vWzGJONPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"457be35a63428c36cb180a1659968825c80c2483c3f5dc411052e2b1c746863d","last_reissued_at":"2026-05-17T23:46:03.575310Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:03.575310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Value Function Polytope in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrien Ali Ta\\\"iga, Dale Schuurmans, Marc G. Bellemare, Nicolas Le Roux, Robert Dadashi","submitted_at":"2019-01-31T18:45:04Z","abstract_excerpt":"We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main contribution is the characterization of the nature of its shape: a general polytope (Aigner et al., 2010). To demonstrate this result, we exhibit several properties of the structural relationship between policies and value functions including the line theorem, which shows that the value functions of policies constrained on all but one state describe a line segment. Finally, we use this novel perspective to introduce visualizations to enhance the understan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11524","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":"1901.11524","created_at":"2026-05-17T23:46:03.575435+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.11524v3","created_at":"2026-05-17T23:46:03.575435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11524","created_at":"2026-05-17T23:46:03.575435+00:00"},{"alias_kind":"pith_short_12","alias_value":"IV56GWTDIKGD","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IV56GWTDIKGDNSYY","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IV56GWTD","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IV56GWTDIKGDNSYYBILFTFUIEX","json":"https://pith.science/pith/IV56GWTDIKGDNSYYBILFTFUIEX.json","graph_json":"https://pith.science/api/pith-number/IV56GWTDIKGDNSYYBILFTFUIEX/graph.json","events_json":"https://pith.science/api/pith-number/IV56GWTDIKGDNSYYBILFTFUIEX/events.json","paper":"https://pith.science/paper/IV56GWTD"},"agent_actions":{"view_html":"https://pith.science/pith/IV56GWTDIKGDNSYYBILFTFUIEX","download_json":"https://pith.science/pith/IV56GWTDIKGDNSYYBILFTFUIEX.json","view_paper":"https://pith.science/paper/IV56GWTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.11524&json=true","fetch_graph":"https://pith.science/api/pith-number/IV56GWTDIKGDNSYYBILFTFUIEX/graph.json","fetch_events":"https://pith.science/api/pith-number/IV56GWTDIKGDNSYYBILFTFUIEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IV56GWTDIKGDNSYYBILFTFUIEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IV56GWTDIKGDNSYYBILFTFUIEX/action/storage_attestation","attest_author":"https://pith.science/pith/IV56GWTDIKGDNSYYBILFTFUIEX/action/author_attestation","sign_citation":"https://pith.science/pith/IV56GWTDIKGDNSYYBILFTFUIEX/action/citation_signature","submit_replication":"https://pith.science/pith/IV56GWTDIKGDNSYYBILFTFUIEX/action/replication_record"}},"created_at":"2026-05-17T23:46:03.575435+00:00","updated_at":"2026-05-17T23:46:03.575435+00:00"}