{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HH42KE4KNDIGPM6TXE3EG4AYJ5","short_pith_number":"pith:HH42KE4K","canonical_record":{"source":{"id":"1802.03976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T11:08:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c926328c1d6d2d85475c908e37340e43f6316e46211d9030fe168c7a3ef01b9c","abstract_canon_sha256":"ba2163bccffeb60e0917fe08ab552ef944d532a581ed241b845dca0420f5e502"},"schema_version":"1.0"},"canonical_sha256":"39f9a5138a68d067b3d3b9364370184f4e629e839c72b5953f14457486aff300","source":{"kind":"arxiv","id":"1802.03976","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03976","created_at":"2026-07-04T23:50:42Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03976v2","created_at":"2026-07-04T23:50:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03976","created_at":"2026-07-04T23:50:42Z"},{"alias_kind":"pith_short_12","alias_value":"HH42KE4KNDIG","created_at":"2026-07-04T23:50:42Z"},{"alias_kind":"pith_short_16","alias_value":"HH42KE4KNDIGPM6T","created_at":"2026-07-04T23:50:42Z"},{"alias_kind":"pith_short_8","alias_value":"HH42KE4K","created_at":"2026-07-04T23:50:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HH42KE4KNDIGPM6TXE3EG4AYJ5","target":"record","payload":{"canonical_record":{"source":{"id":"1802.03976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T11:08:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c926328c1d6d2d85475c908e37340e43f6316e46211d9030fe168c7a3ef01b9c","abstract_canon_sha256":"ba2163bccffeb60e0917fe08ab552ef944d532a581ed241b845dca0420f5e502"},"schema_version":"1.0"},"canonical_sha256":"39f9a5138a68d067b3d3b9364370184f4e629e839c72b5953f14457486aff300","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:50:42.878574Z","signature_b64":"mWq0Up8AgHUndjAZd24cuLNJq3a7CWOp4JPX9PjO3zR5M4qAxJpg+SmU/niul1EcQMYMGxXmQilklLLvabQ3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39f9a5138a68d067b3d3b9364370184f4e629e839c72b5953f14457486aff300","last_reissued_at":"2026-07-04T23:50:42.878076Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:50:42.878076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.03976","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:50:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BFb6rGhGNZ2eEmz0mMp4otW+h9ajJFZTZzLrMzDzicL5EMY6F96Bt4XAz7q2C6zP6Bkl+1efk+pa71Og2GWBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:38:33.849547Z"},"content_sha256":"89a3990eaa5719ac8fe7f947a57f181c3cce38f6a00ce0a0b1f7f1c31f461a28","schema_version":"1.0","event_id":"sha256:89a3990eaa5719ac8fe7f947a57f181c3cce38f6a00ce0a0b1f7f1c31f461a28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HH42KE4KNDIGPM6TXE3EG4AYJ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Wasserstein Distance Regularisation, with Applications to Multipolicy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Moez Draief, Mohammed Amin Abdullah","submitted_at":"2018-02-12T11:08:43Z","abstract_excerpt":"We describe an application of Wasserstein distance to Reinforcement Learning. The Wasserstein distance in question is between the distribution of mappings of trajectories of a policy into some metric space, and some other fixed distribution (which may, for example, come from another policy). Different policies induce different distributions, so given an underlying metric, the Wasserstein distance quantifies how different policies are. This can be used to learn multiple polices which are different in terms of such Wasserstein distances by using a Wasserstein regulariser. Changing the sign of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03976","kind":"arxiv","version":2},"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/1802.03976/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":"2026-07-04T23:50:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1SlK4fqP2aGJ2JlA8QkCHxD6LyLkpURUqJIk9Ujx/LuEGGN66IsDmrmdPdm8hNIsWaeyg11F+U9trulWyLNkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:38:33.850401Z"},"content_sha256":"7f6441806b9e2045f9eb28d9b25e82dfa0e46bed803bd5cf25053a4d759d7515","schema_version":"1.0","event_id":"sha256:7f6441806b9e2045f9eb28d9b25e82dfa0e46bed803bd5cf25053a4d759d7515"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HH42KE4KNDIGPM6TXE3EG4AYJ5/bundle.json","state_url":"https://pith.science/pith/HH42KE4KNDIGPM6TXE3EG4AYJ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HH42KE4KNDIGPM6TXE3EG4AYJ5/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":"2026-08-19T19:38:33Z","links":{"resolver":"https://pith.science/pith/HH42KE4KNDIGPM6TXE3EG4AYJ5","bundle":"https://pith.science/pith/HH42KE4KNDIGPM6TXE3EG4AYJ5/bundle.json","state":"https://pith.science/pith/HH42KE4KNDIGPM6TXE3EG4AYJ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HH42KE4KNDIGPM6TXE3EG4AYJ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HH42KE4KNDIGPM6TXE3EG4AYJ5","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":"ba2163bccffeb60e0917fe08ab552ef944d532a581ed241b845dca0420f5e502","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T11:08:43Z","title_canon_sha256":"c926328c1d6d2d85475c908e37340e43f6316e46211d9030fe168c7a3ef01b9c"},"schema_version":"1.0","source":{"id":"1802.03976","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03976","created_at":"2026-07-04T23:50:42Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03976v2","created_at":"2026-07-04T23:50:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03976","created_at":"2026-07-04T23:50:42Z"},{"alias_kind":"pith_short_12","alias_value":"HH42KE4KNDIG","created_at":"2026-07-04T23:50:42Z"},{"alias_kind":"pith_short_16","alias_value":"HH42KE4KNDIGPM6T","created_at":"2026-07-04T23:50:42Z"},{"alias_kind":"pith_short_8","alias_value":"HH42KE4K","created_at":"2026-07-04T23:50:42Z"}],"graph_snapshots":[{"event_id":"sha256:7f6441806b9e2045f9eb28d9b25e82dfa0e46bed803bd5cf25053a4d759d7515","target":"graph","created_at":"2026-07-04T23:50:42Z","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/1802.03976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We describe an application of Wasserstein distance to Reinforcement Learning. The Wasserstein distance in question is between the distribution of mappings of trajectories of a policy into some metric space, and some other fixed distribution (which may, for example, come from another policy). Different policies induce different distributions, so given an underlying metric, the Wasserstein distance quantifies how different policies are. This can be used to learn multiple polices which are different in terms of such Wasserstein distances by using a Wasserstein regulariser. Changing the sign of th","authors_text":"Aldo Pacchiano, Moez Draief, Mohammed Amin Abdullah","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T11:08:43Z","title":"Reinforcement Learning with Wasserstein Distance Regularisation, with Applications to Multipolicy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03976","kind":"arxiv","version":2},"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":"sha256:89a3990eaa5719ac8fe7f947a57f181c3cce38f6a00ce0a0b1f7f1c31f461a28","target":"record","created_at":"2026-07-04T23:50:42Z","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":"ba2163bccffeb60e0917fe08ab552ef944d532a581ed241b845dca0420f5e502","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T11:08:43Z","title_canon_sha256":"c926328c1d6d2d85475c908e37340e43f6316e46211d9030fe168c7a3ef01b9c"},"schema_version":"1.0","source":{"id":"1802.03976","kind":"arxiv","version":2}},"canonical_sha256":"39f9a5138a68d067b3d3b9364370184f4e629e839c72b5953f14457486aff300","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39f9a5138a68d067b3d3b9364370184f4e629e839c72b5953f14457486aff300","first_computed_at":"2026-07-04T23:50:42.878076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:50:42.878076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mWq0Up8AgHUndjAZd24cuLNJq3a7CWOp4JPX9PjO3zR5M4qAxJpg+SmU/niul1EcQMYMGxXmQilklLLvabQ3AA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:50:42.878574Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.03976","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89a3990eaa5719ac8fe7f947a57f181c3cce38f6a00ce0a0b1f7f1c31f461a28","sha256:7f6441806b9e2045f9eb28d9b25e82dfa0e46bed803bd5cf25053a4d759d7515"],"state_sha256":"e92f44a377696efd913672aa60c784250438f4ac4d238880d1633156a71423b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/8xaJYsrLpyqQUNgBPfN48kj7RLv24akUrDHt9FxSsnoWCPdNy2QOzGnQy4nAFKKD7PPRhwNxI5lQx2QAP5Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T19:38:33.871373Z","bundle_sha256":"afe168b8048566536ff32e04d34cd4f02a67864565404d4b883c403604587189"}}