{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HS34UNCD3W4IUIZRGNTDKJIEMN","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":"b4319707a23ebffc736e22908f4a750c08f4b48c7ee1c25f299d73e8285397a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-23T04:10:58Z","title_canon_sha256":"cc66ac5bd6595deb66242f98397cbf8ce24466d1bcf77ae966729be5f2cd00e7"},"schema_version":"1.0","source":{"id":"2306.13284","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.13284","created_at":"2026-07-05T06:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.13284v1","created_at":"2026-07-05T06:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13284","created_at":"2026-07-05T06:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"HS34UNCD3W4I","created_at":"2026-07-05T06:24:03Z"},{"alias_kind":"pith_short_16","alias_value":"HS34UNCD3W4IUIZR","created_at":"2026-07-05T06:24:03Z"},{"alias_kind":"pith_short_8","alias_value":"HS34UNCD","created_at":"2026-07-05T06:24:03Z"}],"graph_snapshots":[{"event_id":"sha256:09203ac4bbb9dc81a22392278dee896c0dbed07453f4010d39c1cd312028b074","target":"graph","created_at":"2026-07-05T06:24:03Z","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/2306.13284/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The policy gradient theorem gives a convenient form of the policy gradient in terms of three factors: an action value, a gradient of the action likelihood, and a state distribution involving discounting called the \\emph{discounted stationary distribution}. But commonly used on-policy methods based on the policy gradient theorem ignores the discount factor in the state distribution, which is technically incorrect and may even cause degenerate learning behavior in some environments. An existing solution corrects this discrepancy by using $\\gamma^t$ as a factor in the gradient estimate. However, ","authors_text":"A. Rupam Mahmood, Fengdi Che, Gautham Vasan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-23T04:10:58Z","title":"Correcting discount-factor mismatch in on-policy policy gradient methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13284","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":"sha256:03a14c9185a73623f536a7c475f33b5bd95a985c9f84f453e97fea1b1ee3706c","target":"record","created_at":"2026-07-05T06:24:03Z","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":"b4319707a23ebffc736e22908f4a750c08f4b48c7ee1c25f299d73e8285397a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-23T04:10:58Z","title_canon_sha256":"cc66ac5bd6595deb66242f98397cbf8ce24466d1bcf77ae966729be5f2cd00e7"},"schema_version":"1.0","source":{"id":"2306.13284","kind":"arxiv","version":1}},"canonical_sha256":"3cb7ca3443ddb88a2331336635250463600382688269fb3a0e1f5fead4535480","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cb7ca3443ddb88a2331336635250463600382688269fb3a0e1f5fead4535480","first_computed_at":"2026-07-05T06:24:03.683493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:03.683493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jP8V3jyToxmMxHCDmP4AIbr8Poz7fN3O9Rc8gdhEr1hcPIMAjUlySgwKfnr5ofIB0JBu4YmwocovPzRKDqssDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:03.683958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.13284","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03a14c9185a73623f536a7c475f33b5bd95a985c9f84f453e97fea1b1ee3706c","sha256:09203ac4bbb9dc81a22392278dee896c0dbed07453f4010d39c1cd312028b074"],"state_sha256":"f329b517ef41d8e0c8e9e1722a2322756b14eb80616682bf1cb1c2733ccbc19c"}