{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4P7JS2KG2EFB5ESL7WQXJDPCLM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1cf8962668799c0ecc8f25aafa1499469ebe3ac3e1b0f2bcabf8f04bce24bada","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-19T18:43:56Z","title_canon_sha256":"93ef3e03b447d0e60f5c9aa17d64f0f2fbff0393d3055f1596ff44ab82203354"},"schema_version":"1.0","source":{"id":"1909.09186","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.09186","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"1909.09186v1","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.09186","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"4P7JS2KG2EFB","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"4P7JS2KG2EFB5ESL","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"4P7JS2KG","created_at":"2026-07-05T00:05:55Z"}],"graph_snapshots":[{"event_id":"sha256:ca247193d7e8ade4f1fb5a4f208ae265dc8b31f837682a5d99316dd43a66db9f","target":"graph","created_at":"2026-07-05T00:05:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.09186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Doina Precup, Sitao Luan, Xiao-Wen Chang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-19T18:43:56Z","title":"Revisit Policy Optimization in Matrix Form"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.09186","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:365c27d426839acdb9bca1054de81069c2d63298f757650b685ea2668798a771","target":"record","created_at":"2026-07-05T00:05:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1cf8962668799c0ecc8f25aafa1499469ebe3ac3e1b0f2bcabf8f04bce24bada","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-19T18:43:56Z","title_canon_sha256":"93ef3e03b447d0e60f5c9aa17d64f0f2fbff0393d3055f1596ff44ab82203354"},"schema_version":"1.0","source":{"id":"1909.09186","kind":"arxiv","version":1}},"canonical_sha256":"e3fe996946d10a1e924bfda1748de25b18480abd9853deeb78c39a0f631c2be0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3fe996946d10a1e924bfda1748de25b18480abd9853deeb78c39a0f631c2be0","first_computed_at":"2026-07-05T00:05:55.996370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:05:55.996370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i7cCzr4Kwvl1lbWUHOnP2Gh62N6Au005GKtLHrxXpEb3Gm8xHXuWYJy5quipq4/yg/CxfFWHbQBexhyExmutDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:05:55.996826Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.09186","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:365c27d426839acdb9bca1054de81069c2d63298f757650b685ea2668798a771","sha256:ca247193d7e8ade4f1fb5a4f208ae265dc8b31f837682a5d99316dd43a66db9f"],"state_sha256":"e344e163a92375516c0d0c3ccbad28fce1b42c229288b9455aa374b622bdd4d4"}