{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UMT6S4AR66IXGIPIE3UJO6EGCJ","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":"dcc46ee9bb3df1490cb7a3328b3e99af4634d7b150baaafb2c275830fce9acfb","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-05T08:06:29Z","title_canon_sha256":"0187e42d99feebb1f41939ba62137d76a07b57275f91953ff6ea3f05f45858ec"},"schema_version":"1.0","source":{"id":"2209.01820","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.01820","created_at":"2026-07-05T04:54:34Z"},{"alias_kind":"arxiv_version","alias_value":"2209.01820v1","created_at":"2026-07-05T04:54:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.01820","created_at":"2026-07-05T04:54:34Z"},{"alias_kind":"pith_short_12","alias_value":"UMT6S4AR66IX","created_at":"2026-07-05T04:54:34Z"},{"alias_kind":"pith_short_16","alias_value":"UMT6S4AR66IXGIPI","created_at":"2026-07-05T04:54:34Z"},{"alias_kind":"pith_short_8","alias_value":"UMT6S4AR","created_at":"2026-07-05T04:54:34Z"}],"graph_snapshots":[{"event_id":"sha256:9b198889c5de9cbd72f6ea9ce2bd65d98ce0d69a11f89bcfd2b8e880fafa4765","target":"graph","created_at":"2026-07-05T04:54:34Z","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/2209.01820/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional policy gradient methods are fundamentally flawed. Natural gradients converge quicker and better, forming the foundation of contemporary Reinforcement Learning such as Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO). This lecture note aims to clarify the intuition behind natural policy gradients, focusing on the thought process and the key mathematical constructs.","authors_text":"W.J.A. van Heeswijk","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-05T08:06:29Z","title":"Natural Policy Gradients In Reinforcement Learning Explained"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.01820","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":"sha256:8ddc852ae62975088696eddf79830dfd600f00fc8e636f66eb68a4ef1bc2a69c","target":"record","created_at":"2026-07-05T04:54:34Z","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":"dcc46ee9bb3df1490cb7a3328b3e99af4634d7b150baaafb2c275830fce9acfb","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-05T08:06:29Z","title_canon_sha256":"0187e42d99feebb1f41939ba62137d76a07b57275f91953ff6ea3f05f45858ec"},"schema_version":"1.0","source":{"id":"2209.01820","kind":"arxiv","version":1}},"canonical_sha256":"a327e97011f7917321e826e897788612429a8ba620714c4537e7cc63652bc255","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a327e97011f7917321e826e897788612429a8ba620714c4537e7cc63652bc255","first_computed_at":"2026-07-05T04:54:34.310903Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:54:34.310903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eRMHk71ECcqYf5s3CLz/1kK8lCHQa5wbY/3iF7nu24dc889QYNgtJgELFNfCMvr/zQk743OQdSN5Qn//DXSXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:54:34.311242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.01820","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ddc852ae62975088696eddf79830dfd600f00fc8e636f66eb68a4ef1bc2a69c","sha256:9b198889c5de9cbd72f6ea9ce2bd65d98ce0d69a11f89bcfd2b8e880fafa4765"],"state_sha256":"e211881c8c9a2ce0026a9b9fc7be5141c27b97958574f537c64f69707440b376"}