{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:N47KI2ZTSFBNCB5Y5XML4OZXJK","short_pith_number":"pith:N47KI2ZT","schema_version":"1.0","canonical_sha256":"6f3ea46b339142d107b8edd8be3b374aa24dfbedfdde9832ed3cd79918df1ec2","source":{"kind":"arxiv","id":"1808.03030","version":1},"attestation_state":"computed","paper":{"title":"Policy Optimization as Wasserstein Gradient Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Changyou Chen, Chunyuan Li, Lawrence Carin, Ruiyi Zhang","submitted_at":"2018-08-09T06:19:39Z","abstract_excerpt":"Policy optimization is a core component of reinforcement learning (RL), and most existing RL methods directly optimize parameters of a policy based on maximizing the expected total reward, or its surrogate. Though often achieving encouraging empirical success, its underlying mathematical principle on {\\em policy-distribution} optimization is unclear. We place policy optimization into the space of probability measures, and interpret it as Wasserstein gradient flows. On the probability-measure space, under specified circumstances, policy optimization becomes a convex problem in terms of distribu"},"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":"1808.03030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-09T06:19:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f75224472e1db91e22bbe7c4d1ea6e75dd48fdaeff5987f931b07d4cb4f30a5b","abstract_canon_sha256":"23b2de2706caf524d775a8710fc8075b5552970256e6517bec41d3e824b55355"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:30.388518Z","signature_b64":"/oynGSwsZzQ8E2RkV1ixRz5za2Q3hvQHjllui/hGLrx+DPexZNZBUHyklXbQGd+SGPPQEW2H4azk4D94a7IgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f3ea46b339142d107b8edd8be3b374aa24dfbedfdde9832ed3cd79918df1ec2","last_reissued_at":"2026-05-18T00:08:30.388049Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:30.388049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Optimization as Wasserstein Gradient Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Changyou Chen, Chunyuan Li, Lawrence Carin, Ruiyi Zhang","submitted_at":"2018-08-09T06:19:39Z","abstract_excerpt":"Policy optimization is a core component of reinforcement learning (RL), and most existing RL methods directly optimize parameters of a policy based on maximizing the expected total reward, or its surrogate. Though often achieving encouraging empirical success, its underlying mathematical principle on {\\em policy-distribution} optimization is unclear. We place policy optimization into the space of probability measures, and interpret it as Wasserstein gradient flows. On the probability-measure space, under specified circumstances, policy optimization becomes a convex problem in terms of distribu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.03030","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1808.03030","created_at":"2026-05-18T00:08:30.388118+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.03030v1","created_at":"2026-05-18T00:08:30.388118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03030","created_at":"2026-05-18T00:08:30.388118+00:00"},{"alias_kind":"pith_short_12","alias_value":"N47KI2ZTSFBN","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"N47KI2ZTSFBNCB5Y","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"N47KI2ZT","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK","json":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK.json","graph_json":"https://pith.science/api/pith-number/N47KI2ZTSFBNCB5Y5XML4OZXJK/graph.json","events_json":"https://pith.science/api/pith-number/N47KI2ZTSFBNCB5Y5XML4OZXJK/events.json","paper":"https://pith.science/paper/N47KI2ZT"},"agent_actions":{"view_html":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK","download_json":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK.json","view_paper":"https://pith.science/paper/N47KI2ZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.03030&json=true","fetch_graph":"https://pith.science/api/pith-number/N47KI2ZTSFBNCB5Y5XML4OZXJK/graph.json","fetch_events":"https://pith.science/api/pith-number/N47KI2ZTSFBNCB5Y5XML4OZXJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK/action/storage_attestation","attest_author":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK/action/author_attestation","sign_citation":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK/action/citation_signature","submit_replication":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK/action/replication_record"}},"created_at":"2026-05-18T00:08:30.388118+00:00","updated_at":"2026-05-18T00:08:30.388118+00:00"}