{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NBVHSVZPJCY3C3ILOXMKDIJKBX","short_pith_number":"pith:NBVHSVZP","schema_version":"1.0","canonical_sha256":"686a79572f48b1b16d0b75d8a1a12a0dd39d6d28345c0484f0ecb5e2106d6a53","source":{"kind":"arxiv","id":"1707.02747","version":2},"attestation_state":"computed","paper":{"title":"Robust Imitation of Diverse Behaviors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Greg Wayne, Josh Merel, Nando de Freitas, Nicolas Heess, Scott Reed, Ziyu Wang","submitted_at":"2017-07-10T08:46:14Z","abstract_excerpt":"Deep generative models have recently shown great promise in imitation learning for motor control. Given enough data, even supervised approaches can do one-shot imitation learning; however, they are vulnerable to cascading failures when the agent trajectory diverges from the demonstrations. Compared to purely supervised methods, Generative Adversarial Imitation Learning (GAIL) can learn more robust controllers from fewer demonstrations, but is inherently mode-seeking and more difficult to train. In this paper, we show how to combine the favourable aspects of these two approaches. The base of ou"},"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":"1707.02747","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-10T08:46:14Z","cross_cats_sorted":[],"title_canon_sha256":"4553cc96eae9ab136109501ca2459c9b707cdbeb3a781caf089e1def108fed2a","abstract_canon_sha256":"e08c3de0f56bed418afd3e29c4cb619f5290868d8e590a31354d2fd1a1dbe9da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:18.895944Z","signature_b64":"hUwWyrCKQB9SC+AhO7oXHJwUgKcskIWNf1Fwz6JDzzse5XrrBzVEgbKjLlUGHVOQSiE/p4uMf++e3PPJMNThBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"686a79572f48b1b16d0b75d8a1a12a0dd39d6d28345c0484f0ecb5e2106d6a53","last_reissued_at":"2026-05-18T00:40:18.895288Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:18.895288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Imitation of Diverse Behaviors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Greg Wayne, Josh Merel, Nando de Freitas, Nicolas Heess, Scott Reed, Ziyu Wang","submitted_at":"2017-07-10T08:46:14Z","abstract_excerpt":"Deep generative models have recently shown great promise in imitation learning for motor control. Given enough data, even supervised approaches can do one-shot imitation learning; however, they are vulnerable to cascading failures when the agent trajectory diverges from the demonstrations. Compared to purely supervised methods, Generative Adversarial Imitation Learning (GAIL) can learn more robust controllers from fewer demonstrations, but is inherently mode-seeking and more difficult to train. In this paper, we show how to combine the favourable aspects of these two approaches. The base of ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.02747","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":""},"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":"1707.02747","created_at":"2026-05-18T00:40:18.895387+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.02747v2","created_at":"2026-05-18T00:40:18.895387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02747","created_at":"2026-05-18T00:40:18.895387+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBVHSVZPJCY3","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBVHSVZPJCY3C3IL","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBVHSVZP","created_at":"2026-05-18T12:31:31.346846+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/NBVHSVZPJCY3C3ILOXMKDIJKBX","json":"https://pith.science/pith/NBVHSVZPJCY3C3ILOXMKDIJKBX.json","graph_json":"https://pith.science/api/pith-number/NBVHSVZPJCY3C3ILOXMKDIJKBX/graph.json","events_json":"https://pith.science/api/pith-number/NBVHSVZPJCY3C3ILOXMKDIJKBX/events.json","paper":"https://pith.science/paper/NBVHSVZP"},"agent_actions":{"view_html":"https://pith.science/pith/NBVHSVZPJCY3C3ILOXMKDIJKBX","download_json":"https://pith.science/pith/NBVHSVZPJCY3C3ILOXMKDIJKBX.json","view_paper":"https://pith.science/paper/NBVHSVZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.02747&json=true","fetch_graph":"https://pith.science/api/pith-number/NBVHSVZPJCY3C3ILOXMKDIJKBX/graph.json","fetch_events":"https://pith.science/api/pith-number/NBVHSVZPJCY3C3ILOXMKDIJKBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBVHSVZPJCY3C3ILOXMKDIJKBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBVHSVZPJCY3C3ILOXMKDIJKBX/action/storage_attestation","attest_author":"https://pith.science/pith/NBVHSVZPJCY3C3ILOXMKDIJKBX/action/author_attestation","sign_citation":"https://pith.science/pith/NBVHSVZPJCY3C3ILOXMKDIJKBX/action/citation_signature","submit_replication":"https://pith.science/pith/NBVHSVZPJCY3C3ILOXMKDIJKBX/action/replication_record"}},"created_at":"2026-05-18T00:40:18.895387+00:00","updated_at":"2026-05-18T00:40:18.895387+00:00"}