{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4P7JS2KG2EFB5ESL7WQXJDPCLM","short_pith_number":"pith:4P7JS2KG","schema_version":"1.0","canonical_sha256":"e3fe996946d10a1e924bfda1748de25b18480abd9853deeb78c39a0f631c2be0","source":{"kind":"arxiv","id":"1909.09186","version":1},"attestation_state":"computed","paper":{"title":"Revisit Policy Optimization in Matrix Form","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Sitao Luan, Xiao-Wen Chang","submitted_at":"2019-09-19T18:43:56Z","abstract_excerpt":"In tabular case, when the reward and environment dynamics are known, policy evaluation can be written as $\\bm{V}_{\\bm{\\pi}} = (I - \\gamma P_{\\bm{\\pi}})^{-1} \\bm{r}_{\\bm{\\pi}}$, where $P_{\\bm{\\pi}}$ is the state transition matrix given policy ${\\bm{\\pi}}$ and $\\bm{r}_{\\bm{\\pi}}$ is the reward signal given ${\\bm{\\pi}}$. What annoys us is that $P_{\\bm{\\pi}}$ and $\\bm{r}_{\\bm{\\pi}}$ are both mixed with ${\\bm{\\pi}}$, which means every time when we update ${\\bm{\\pi}}$, they will change together. In this paper, we leverage the notation from \\cite{wang2007dual} to disentangle ${\\bm{\\pi}}$ and environm"},"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":"1909.09186","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-19T18:43:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93ef3e03b447d0e60f5c9aa17d64f0f2fbff0393d3055f1596ff44ab82203354","abstract_canon_sha256":"1cf8962668799c0ecc8f25aafa1499469ebe3ac3e1b0f2bcabf8f04bce24bada"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:05:55.996826Z","signature_b64":"i7cCzr4Kwvl1lbWUHOnP2Gh62N6Au005GKtLHrxXpEb3Gm8xHXuWYJy5quipq4/yg/CxfFWHbQBexhyExmutDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3fe996946d10a1e924bfda1748de25b18480abd9853deeb78c39a0f631c2be0","last_reissued_at":"2026-07-05T00:05:55.996370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:05:55.996370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisit Policy Optimization in Matrix Form","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Sitao Luan, Xiao-Wen Chang","submitted_at":"2019-09-19T18:43:56Z","abstract_excerpt":"In tabular case, when the reward and environment dynamics are known, policy evaluation can be written as $\\bm{V}_{\\bm{\\pi}} = (I - \\gamma P_{\\bm{\\pi}})^{-1} \\bm{r}_{\\bm{\\pi}}$, where $P_{\\bm{\\pi}}$ is the state transition matrix given policy ${\\bm{\\pi}}$ and $\\bm{r}_{\\bm{\\pi}}$ is the reward signal given ${\\bm{\\pi}}$. What annoys us is that $P_{\\bm{\\pi}}$ and $\\bm{r}_{\\bm{\\pi}}$ are both mixed with ${\\bm{\\pi}}$, which means every time when we update ${\\bm{\\pi}}$, they will change together. In this paper, we leverage the notation from \\cite{wang2007dual} to disentangle ${\\bm{\\pi}}$ and environm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.09186","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/1909.09186/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":"1909.09186","created_at":"2026-07-05T00:05:55.996428+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.09186v1","created_at":"2026-07-05T00:05:55.996428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.09186","created_at":"2026-07-05T00:05:55.996428+00:00"},{"alias_kind":"pith_short_12","alias_value":"4P7JS2KG2EFB","created_at":"2026-07-05T00:05:55.996428+00:00"},{"alias_kind":"pith_short_16","alias_value":"4P7JS2KG2EFB5ESL","created_at":"2026-07-05T00:05:55.996428+00:00"},{"alias_kind":"pith_short_8","alias_value":"4P7JS2KG","created_at":"2026-07-05T00:05:55.996428+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/4P7JS2KG2EFB5ESL7WQXJDPCLM","json":"https://pith.science/pith/4P7JS2KG2EFB5ESL7WQXJDPCLM.json","graph_json":"https://pith.science/api/pith-number/4P7JS2KG2EFB5ESL7WQXJDPCLM/graph.json","events_json":"https://pith.science/api/pith-number/4P7JS2KG2EFB5ESL7WQXJDPCLM/events.json","paper":"https://pith.science/paper/4P7JS2KG"},"agent_actions":{"view_html":"https://pith.science/pith/4P7JS2KG2EFB5ESL7WQXJDPCLM","download_json":"https://pith.science/pith/4P7JS2KG2EFB5ESL7WQXJDPCLM.json","view_paper":"https://pith.science/paper/4P7JS2KG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.09186&json=true","fetch_graph":"https://pith.science/api/pith-number/4P7JS2KG2EFB5ESL7WQXJDPCLM/graph.json","fetch_events":"https://pith.science/api/pith-number/4P7JS2KG2EFB5ESL7WQXJDPCLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4P7JS2KG2EFB5ESL7WQXJDPCLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4P7JS2KG2EFB5ESL7WQXJDPCLM/action/storage_attestation","attest_author":"https://pith.science/pith/4P7JS2KG2EFB5ESL7WQXJDPCLM/action/author_attestation","sign_citation":"https://pith.science/pith/4P7JS2KG2EFB5ESL7WQXJDPCLM/action/citation_signature","submit_replication":"https://pith.science/pith/4P7JS2KG2EFB5ESL7WQXJDPCLM/action/replication_record"}},"created_at":"2026-07-05T00:05:55.996428+00:00","updated_at":"2026-07-05T00:05:55.996428+00:00"}