{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5T4KTDRHKKVA37U3DWSYSASRQL","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":"87d163e9fa6188eceed4e5fec662a37a5c96a3ecc936fe7c001d6a181265a814","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-19T20:05:06Z","title_canon_sha256":"d090aedc584432b4c717b2149e6dc5a445d19cf29c7a1c380fa969f0fe2e517d"},"schema_version":"1.0","source":{"id":"1712.07185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.07185","created_at":"2026-05-18T00:27:35Z"},{"alias_kind":"arxiv_version","alias_value":"1712.07185v1","created_at":"2026-05-18T00:27:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07185","created_at":"2026-05-18T00:27:35Z"},{"alias_kind":"pith_short_12","alias_value":"5T4KTDRHKKVA","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5T4KTDRHKKVA37U3","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5T4KTDRH","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:9dff046afcb55e19f02297686a7af0b3ab7b049e26fcae1b2ef32195985ec1bb","target":"graph","created_at":"2026-05-18T00:27:35Z","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 gradients methods often achieve better performance when the change in policy is limited to a small Kullback-Leibler divergence. We derive policy gradients where the change in policy is limited to a small Wasserstein distance (or trust region). This is done in the discrete and continuous multi-armed bandit settings with entropy regularisation. We show that in the small steps limit with respect to the Wasserstein distance $W_2$, policy dynamics are governed by the Fokker-Planck (heat) equation, following the Jordan-Kinderlehrer-Otto result. This means that policies undergo diffusion and a","authors_text":"Brendan Maginnis, Pierre H. Richemond","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-19T20:05:06Z","title":"On Wasserstein Reinforcement Learning and the Fokker-Planck equation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.07185","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":"sha256:34554866f5717b410563c0663a354a9a3bed5af7f4658af43067f12418cafcf5","target":"record","created_at":"2026-05-18T00:27:35Z","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":"87d163e9fa6188eceed4e5fec662a37a5c96a3ecc936fe7c001d6a181265a814","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-19T20:05:06Z","title_canon_sha256":"d090aedc584432b4c717b2149e6dc5a445d19cf29c7a1c380fa969f0fe2e517d"},"schema_version":"1.0","source":{"id":"1712.07185","kind":"arxiv","version":1}},"canonical_sha256":"ecf8a98e2752aa0dfe9b1da589025182ea76e52ee4c48175e2936955aa25474d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecf8a98e2752aa0dfe9b1da589025182ea76e52ee4c48175e2936955aa25474d","first_computed_at":"2026-05-18T00:27:35.309945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:35.309945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZpZ0d+GHQ7q6USRNrIT5KWlkT9c8nn+Day1h2kXF6baxm5l12HsxzrlV2yYsx9GC5irwibhzEF6w226Cy+c5Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:35.310575Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.07185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34554866f5717b410563c0663a354a9a3bed5af7f4658af43067f12418cafcf5","sha256:9dff046afcb55e19f02297686a7af0b3ab7b049e26fcae1b2ef32195985ec1bb"],"state_sha256":"b49682e6d4727c2b52cbb16f092ec9c8a3c4d959cc8dc4d58569f8ce639414f8"}