{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VGAUTTP2WKC7BR7UR66NX5NNS4","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":"4abc957b3621fc93bfd7eb12d3eff1f055e74b0c3f609cc421e2bf9b07ab187e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-04T21:23:33Z","title_canon_sha256":"61423959c0216d14d6c58f4417f0bfc5479f9b5271844e8664e61224258f3e39"},"schema_version":"1.0","source":{"id":"2202.02396","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.02396","created_at":"2026-07-05T04:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2202.02396v4","created_at":"2026-07-05T04:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02396","created_at":"2026-07-05T04:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"VGAUTTP2WKC7","created_at":"2026-07-05T04:38:13Z"},{"alias_kind":"pith_short_16","alias_value":"VGAUTTP2WKC7BR7U","created_at":"2026-07-05T04:38:13Z"},{"alias_kind":"pith_short_8","alias_value":"VGAUTTP2","created_at":"2026-07-05T04:38:13Z"}],"graph_snapshots":[{"event_id":"sha256:0a2b43f31411d14f602758df403ba2982e4e9c6eaa55a40574701883ad1df0d1","target":"graph","created_at":"2026-07-05T04:38:13Z","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/2202.02396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The policy gradient theorem (Sutton et al., 2000) prescribes the usage of a cumulative discounted state distribution under the target policy to approximate the gradient. Most algorithms based on this theorem, in practice, break this assumption, introducing a distribution shift that can cause the convergence to poor solutions. In this paper, we propose a new approach of reconstructing the policy gradient from the start state without requiring a particular sampling strategy. The policy gradient calculation in this form can be simplified in terms of a gradient critic, which can be recursively est","authors_text":"Andrew Patterson, A. Rupam Mahmood, Martha White, Samuele Tosatto","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-04T21:23:33Z","title":"A Temporal-Difference Approach to Policy Gradient Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02396","kind":"arxiv","version":4},"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":"sha256:8fb3b8c813bd521ec835ed84502dc8fcee1d12afceedf4f561c611c527521bfb","target":"record","created_at":"2026-07-05T04:38:13Z","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":"4abc957b3621fc93bfd7eb12d3eff1f055e74b0c3f609cc421e2bf9b07ab187e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-04T21:23:33Z","title_canon_sha256":"61423959c0216d14d6c58f4417f0bfc5479f9b5271844e8664e61224258f3e39"},"schema_version":"1.0","source":{"id":"2202.02396","kind":"arxiv","version":4}},"canonical_sha256":"a98149cdfab285f0c7f48fbcdbf5ad9717299a6fd38cfb4c9c535957ab837f39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a98149cdfab285f0c7f48fbcdbf5ad9717299a6fd38cfb4c9c535957ab837f39","first_computed_at":"2026-07-05T04:38:13.802397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:38:13.802397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"99KsVrRrRvYoMM07NiZweAPggqkgbt0WMnDFoFlAYioSsJWUjSh1/t2nGZR2q5TGlUdodx/Uf3CUsGDE6/fdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:38:13.802824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.02396","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fb3b8c813bd521ec835ed84502dc8fcee1d12afceedf4f561c611c527521bfb","sha256:0a2b43f31411d14f602758df403ba2982e4e9c6eaa55a40574701883ad1df0d1"],"state_sha256":"cb202b2b94023d1cf9ae455f80934c01942ea7156687e6951a409d5df1171f3f"}