{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DKXN2S3IETRZAYXV6BGOFQOAYI","short_pith_number":"pith:DKXN2S3I","schema_version":"1.0","canonical_sha256":"1aaedd4b6824e39062f5f04ce2c1c0c205a6993df7017a4d529ab510c878acc1","source":{"kind":"arxiv","id":"1810.07900","version":3},"attestation_state":"computed","paper":{"title":"Policy Gradient in Partially Observable Environments: Approximation and Convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Animashree Anandkumar, Kamyar Azizzadenesheli, Yisong Yue","submitted_at":"2018-10-18T05:25:11Z","abstract_excerpt":"Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced for fully observable environments. In this paper, we generalize a variety of these advances to partially observable settings, and similar to the fully observable case, we keep our focus on the class of Markovian policies. We propose a series of technical tools, including a novel notion of advantage function, to develop policy gradient algorithms and study their convergence pro"},"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":"1810.07900","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-18T05:25:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dcbf8a1d7948d35ae66f12f5c7f32d5d200fb8221c93120631594809df435d1f","abstract_canon_sha256":"2c1387bb6c4e581d9ad8fbdcfd5bdf5d74c7ba76cd1e271ec002fb9af0666cbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:22.816435Z","signature_b64":"SGDdwb6KNe+HDQVmgxeRZy/P7JXDUtFUS6gLXLIZIITr0V5sn/pJXWG6qszHMXudQgH2c397l275I7ZTWXi+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1aaedd4b6824e39062f5f04ce2c1c0c205a6993df7017a4d529ab510c878acc1","last_reissued_at":"2026-07-05T01:05:22.815898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:22.815898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Gradient in Partially Observable Environments: Approximation and Convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Animashree Anandkumar, Kamyar Azizzadenesheli, Yisong Yue","submitted_at":"2018-10-18T05:25:11Z","abstract_excerpt":"Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced for fully observable environments. In this paper, we generalize a variety of these advances to partially observable settings, and similar to the fully observable case, we keep our focus on the class of Markovian policies. We propose a series of technical tools, including a novel notion of advantage function, to develop policy gradient algorithms and study their convergence pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07900","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1810.07900/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":"1810.07900","created_at":"2026-07-05T01:05:22.815963+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07900v3","created_at":"2026-07-05T01:05:22.815963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07900","created_at":"2026-07-05T01:05:22.815963+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKXN2S3IETRZ","created_at":"2026-07-05T01:05:22.815963+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKXN2S3IETRZAYXV","created_at":"2026-07-05T01:05:22.815963+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKXN2S3I","created_at":"2026-07-05T01:05:22.815963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03048","citing_title":"The Value Function Semi-Algebraic Set in Partially Observable Markov Decision Processes","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"1906.11075","citing_title":"Optimistic Proximal Policy Optimization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12181","citing_title":"Action-Gradient Monte Carlo Tree Search for Non-Parametric Continuous (PO)MDPs","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI","json":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI.json","graph_json":"https://pith.science/api/pith-number/DKXN2S3IETRZAYXV6BGOFQOAYI/graph.json","events_json":"https://pith.science/api/pith-number/DKXN2S3IETRZAYXV6BGOFQOAYI/events.json","paper":"https://pith.science/paper/DKXN2S3I"},"agent_actions":{"view_html":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI","download_json":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI.json","view_paper":"https://pith.science/paper/DKXN2S3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07900&json=true","fetch_graph":"https://pith.science/api/pith-number/DKXN2S3IETRZAYXV6BGOFQOAYI/graph.json","fetch_events":"https://pith.science/api/pith-number/DKXN2S3IETRZAYXV6BGOFQOAYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI/action/storage_attestation","attest_author":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI/action/author_attestation","sign_citation":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI/action/citation_signature","submit_replication":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI/action/replication_record"}},"created_at":"2026-07-05T01:05:22.815963+00:00","updated_at":"2026-07-05T01:05:22.815963+00:00"}