{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DKXN2S3IETRZAYXV6BGOFQOAYI","short_pith_number":"pith:DKXN2S3I","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"},"canonical_sha256":"1aaedd4b6824e39062f5f04ce2c1c0c205a6993df7017a4d529ab510c878acc1","source":{"kind":"arxiv","id":"1810.07900","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.07900","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"1810.07900v3","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07900","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"DKXN2S3IETRZ","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"DKXN2S3IETRZAYXV","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"DKXN2S3I","created_at":"2026-07-05T01:05:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DKXN2S3IETRZAYXV6BGOFQOAYI","target":"record","payload":{"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"},"canonical_sha256":"1aaedd4b6824e39062f5f04ce2c1c0c205a6993df7017a4d529ab510c878acc1","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"},"source_kind":"arxiv","source_id":"1810.07900","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:05:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D1umxSDEIcjgFoSMfRToVLiD+tOhujkQz0UEWHLWIDhJV6KPx+mQSAyfavpBx19EIGL+shvWmMXDLMTpAcqqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:58:48.164965Z"},"content_sha256":"32aa310601f8c420f249a1780c5836aae7f55f3df6b0c84742585ed0219cb3e8","schema_version":"1.0","event_id":"sha256:32aa310601f8c420f249a1780c5836aae7f55f3df6b0c84742585ed0219cb3e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DKXN2S3IETRZAYXV6BGOFQOAYI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:05:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tPz445hdvt4/WGL1N0GUA8SuhIgI28ixPnCh8nz6zhrym6KhKkafUi5NkBVMSA0cIEm7HTnF2GoZVLCVWtcIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:58:48.165487Z"},"content_sha256":"a23793b437e519935e62148304dbd77e88da0a8d496d575cf954d8a886d1b80d","schema_version":"1.0","event_id":"sha256:a23793b437e519935e62148304dbd77e88da0a8d496d575cf954d8a886d1b80d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI/bundle.json","state_url":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DKXN2S3IETRZAYXV6BGOFQOAYI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T20:58:48Z","links":{"resolver":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI","bundle":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI/bundle.json","state":"https://pith.science/pith/DKXN2S3IETRZAYXV6BGOFQOAYI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DKXN2S3IETRZAYXV6BGOFQOAYI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DKXN2S3IETRZAYXV6BGOFQOAYI","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":"2c1387bb6c4e581d9ad8fbdcfd5bdf5d74c7ba76cd1e271ec002fb9af0666cbe","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-18T05:25:11Z","title_canon_sha256":"dcbf8a1d7948d35ae66f12f5c7f32d5d200fb8221c93120631594809df435d1f"},"schema_version":"1.0","source":{"id":"1810.07900","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.07900","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"1810.07900v3","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07900","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"DKXN2S3IETRZ","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"DKXN2S3IETRZAYXV","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"DKXN2S3I","created_at":"2026-07-05T01:05:22Z"}],"graph_snapshots":[{"event_id":"sha256:a23793b437e519935e62148304dbd77e88da0a8d496d575cf954d8a886d1b80d","target":"graph","created_at":"2026-07-05T01:05:22Z","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/1810.07900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Animashree Anandkumar, Kamyar Azizzadenesheli, Yisong Yue","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-18T05:25:11Z","title":"Policy Gradient in Partially Observable Environments: Approximation and Convergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07900","kind":"arxiv","version":3},"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":"sha256:32aa310601f8c420f249a1780c5836aae7f55f3df6b0c84742585ed0219cb3e8","target":"record","created_at":"2026-07-05T01:05:22Z","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":"2c1387bb6c4e581d9ad8fbdcfd5bdf5d74c7ba76cd1e271ec002fb9af0666cbe","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-18T05:25:11Z","title_canon_sha256":"dcbf8a1d7948d35ae66f12f5c7f32d5d200fb8221c93120631594809df435d1f"},"schema_version":"1.0","source":{"id":"1810.07900","kind":"arxiv","version":3}},"canonical_sha256":"1aaedd4b6824e39062f5f04ce2c1c0c205a6993df7017a4d529ab510c878acc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1aaedd4b6824e39062f5f04ce2c1c0c205a6993df7017a4d529ab510c878acc1","first_computed_at":"2026-07-05T01:05:22.815898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:22.815898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SGDdwb6KNe+HDQVmgxeRZy/P7JXDUtFUS6gLXLIZIITr0V5sn/pJXWG6qszHMXudQgH2c397l275I7ZTWXi+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:22.816435Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.07900","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32aa310601f8c420f249a1780c5836aae7f55f3df6b0c84742585ed0219cb3e8","sha256:a23793b437e519935e62148304dbd77e88da0a8d496d575cf954d8a886d1b80d"],"state_sha256":"fb669be66b6e01d120a86e91b8c83474cf50cf29fe12ca86fdc821ba5d0fd9da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W7VfJT9BUuB75N8r51YkZCrqWsxjsBDOtMmMkluzijJAFUo7lWQYxEs3ideNIF2eLLhH8GcycK5e6fb6uNmjDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:58:48.170924Z","bundle_sha256":"1e37d03c5469216045a91d98a6d5c4f677f8885d4edef6318122288b5c735259"}}