{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:N47KI2ZTSFBNCB5Y5XML4OZXJK","short_pith_number":"pith:N47KI2ZT","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"},"canonical_sha256":"6f3ea46b339142d107b8edd8be3b374aa24dfbedfdde9832ed3cd79918df1ec2","source":{"kind":"arxiv","id":"1808.03030","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.03030","created_at":"2026-05-18T00:08:30Z"},{"alias_kind":"arxiv_version","alias_value":"1808.03030v1","created_at":"2026-05-18T00:08:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03030","created_at":"2026-05-18T00:08:30Z"},{"alias_kind":"pith_short_12","alias_value":"N47KI2ZTSFBN","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"N47KI2ZTSFBNCB5Y","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"N47KI2ZT","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:N47KI2ZTSFBNCB5Y5XML4OZXJK","target":"record","payload":{"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"},"canonical_sha256":"6f3ea46b339142d107b8edd8be3b374aa24dfbedfdde9832ed3cd79918df1ec2","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"},"source_kind":"arxiv","source_id":"1808.03030","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:08:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x+3uAOataCX/q1NR9o+miXxptRMx2c2e3rdNMd+7ZpKlUCojwcBS4VMCIkK5O+OhnwW1/qknBUskma6cWGq/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:30:47.524044Z"},"content_sha256":"97805a245783dc0db4e3f32b0ff12fa7fd0a00ccddba4ad0e6a09ed4d97cf6d2","schema_version":"1.0","event_id":"sha256:97805a245783dc0db4e3f32b0ff12fa7fd0a00ccddba4ad0e6a09ed4d97cf6d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:N47KI2ZTSFBNCB5Y5XML4OZXJK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:08:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ov2LwLTM2bsUWvU5DFHowOPYTLbEFi3FlM3dr61GO0bfwhDGvT0JFFkEtXZtSsjAcibr/AYrlKG+RoR/+yEVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:30:47.524420Z"},"content_sha256":"f70dc5e6f8fdf36634d8c64023bbe56ba5054609b52cf19bc137f944ff4f80cb","schema_version":"1.0","event_id":"sha256:f70dc5e6f8fdf36634d8c64023bbe56ba5054609b52cf19bc137f944ff4f80cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK/bundle.json","state_url":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK/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":"2026-05-26T19:30:47Z","links":{"resolver":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK","bundle":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK/bundle.json","state":"https://pith.science/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N47KI2ZTSFBNCB5Y5XML4OZXJK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:N47KI2ZTSFBNCB5Y5XML4OZXJK","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":"23b2de2706caf524d775a8710fc8075b5552970256e6517bec41d3e824b55355","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-09T06:19:39Z","title_canon_sha256":"f75224472e1db91e22bbe7c4d1ea6e75dd48fdaeff5987f931b07d4cb4f30a5b"},"schema_version":"1.0","source":{"id":"1808.03030","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.03030","created_at":"2026-05-18T00:08:30Z"},{"alias_kind":"arxiv_version","alias_value":"1808.03030v1","created_at":"2026-05-18T00:08:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03030","created_at":"2026-05-18T00:08:30Z"},{"alias_kind":"pith_short_12","alias_value":"N47KI2ZTSFBN","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"N47KI2ZTSFBNCB5Y","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"N47KI2ZT","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:f70dc5e6f8fdf36634d8c64023bbe56ba5054609b52cf19bc137f944ff4f80cb","target":"graph","created_at":"2026-05-18T00:08:30Z","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"},"paper":{"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","authors_text":"Changyou Chen, Chunyuan Li, Lawrence Carin, Ruiyi Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-09T06:19:39Z","title":"Policy Optimization as Wasserstein Gradient Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.03030","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":"sha256:97805a245783dc0db4e3f32b0ff12fa7fd0a00ccddba4ad0e6a09ed4d97cf6d2","target":"record","created_at":"2026-05-18T00:08:30Z","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":"23b2de2706caf524d775a8710fc8075b5552970256e6517bec41d3e824b55355","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-09T06:19:39Z","title_canon_sha256":"f75224472e1db91e22bbe7c4d1ea6e75dd48fdaeff5987f931b07d4cb4f30a5b"},"schema_version":"1.0","source":{"id":"1808.03030","kind":"arxiv","version":1}},"canonical_sha256":"6f3ea46b339142d107b8edd8be3b374aa24dfbedfdde9832ed3cd79918df1ec2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f3ea46b339142d107b8edd8be3b374aa24dfbedfdde9832ed3cd79918df1ec2","first_computed_at":"2026-05-18T00:08:30.388049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:30.388049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/oynGSwsZzQ8E2RkV1ixRz5za2Q3hvQHjllui/hGLrx+DPexZNZBUHyklXbQGd+SGPPQEW2H4azk4D94a7IgCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:30.388518Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.03030","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97805a245783dc0db4e3f32b0ff12fa7fd0a00ccddba4ad0e6a09ed4d97cf6d2","sha256:f70dc5e6f8fdf36634d8c64023bbe56ba5054609b52cf19bc137f944ff4f80cb"],"state_sha256":"307ac335448a3844a04d259a49ec6bf6bc3f088453559a2c3fd1d82839ebf3ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4FmBaYHq/SBt8T1C5wTs2+eB0ajVhZ8DZ3pGIZ3rJYemD9LrkEDuQfeOGIARIhw/qYw/zhTNmbIJuxuGtNs1Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T19:30:47.527095Z","bundle_sha256":"ef10cc6500e1e227c61e709d027a72df4408ba3578f9dc93eeb09f4626b7be25"}}