{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:MQ6YXNCUJEFQOR3366SWKBJHMT","short_pith_number":"pith:MQ6YXNCU","schema_version":"1.0","canonical_sha256":"643d8bb454490b07477bf7a565052764f1a32974c78ea50bc96b5b82532395af","source":{"kind":"arxiv","id":"1703.01030","version":1},"attestation_state":"computed","paper":{"title":"Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arun Venkatraman, Byron Boots, Geoffrey J. Gordon, J. Andrew Bagnell, Wen Sun","submitted_at":"2017-03-03T04:12:03Z","abstract_excerpt":"Researchers have demonstrated state-of-the-art performance in sequential decision making problems (e.g., robotics control, sequential prediction) with deep neural network models. One often has access to near-optimal oracles that achieve good performance on the task during training. We demonstrate that AggreVaTeD --- a policy gradient extension of the Imitation Learning (IL) approach of (Ross & Bagnell, 2014) --- can leverage such an oracle to achieve faster and better solutions with less training data than a less-informed Reinforcement Learning (RL) technique. Using both feedforward and recurr"},"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":"1703.01030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-03T04:12:03Z","cross_cats_sorted":[],"title_canon_sha256":"63696ceba1529864c263ef3f8044870bcd7a29e7e3c20ef0dcd51219ab70ded2","abstract_canon_sha256":"63b23a5ac73132959bc96c958c2afc38e46b53bfb15db82e5148a3d00ab6dc58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:37.183226Z","signature_b64":"JjxR6tkDUhooXmZtvcifgG/G82akv+3HP2pDWmy+3EH8U+RNy6Vsizn4/e7f/6/sdMgwh22cqDKwTmh1cau6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"643d8bb454490b07477bf7a565052764f1a32974c78ea50bc96b5b82532395af","last_reissued_at":"2026-05-18T00:49:37.182516Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:37.182516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arun Venkatraman, Byron Boots, Geoffrey J. Gordon, J. Andrew Bagnell, Wen Sun","submitted_at":"2017-03-03T04:12:03Z","abstract_excerpt":"Researchers have demonstrated state-of-the-art performance in sequential decision making problems (e.g., robotics control, sequential prediction) with deep neural network models. One often has access to near-optimal oracles that achieve good performance on the task during training. We demonstrate that AggreVaTeD --- a policy gradient extension of the Imitation Learning (IL) approach of (Ross & Bagnell, 2014) --- can leverage such an oracle to achieve faster and better solutions with less training data than a less-informed Reinforcement Learning (RL) technique. Using both feedforward and recurr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01030","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":"1703.01030","created_at":"2026-05-18T00:49:37.182646+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.01030v1","created_at":"2026-05-18T00:49:37.182646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01030","created_at":"2026-05-18T00:49:37.182646+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQ6YXNCUJEFQ","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQ6YXNCUJEFQOR33","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQ6YXNCU","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/MQ6YXNCUJEFQOR3366SWKBJHMT","json":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT.json","graph_json":"https://pith.science/api/pith-number/MQ6YXNCUJEFQOR3366SWKBJHMT/graph.json","events_json":"https://pith.science/api/pith-number/MQ6YXNCUJEFQOR3366SWKBJHMT/events.json","paper":"https://pith.science/paper/MQ6YXNCU"},"agent_actions":{"view_html":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT","download_json":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT.json","view_paper":"https://pith.science/paper/MQ6YXNCU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.01030&json=true","fetch_graph":"https://pith.science/api/pith-number/MQ6YXNCUJEFQOR3366SWKBJHMT/graph.json","fetch_events":"https://pith.science/api/pith-number/MQ6YXNCUJEFQOR3366SWKBJHMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT/action/storage_attestation","attest_author":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT/action/author_attestation","sign_citation":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT/action/citation_signature","submit_replication":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT/action/replication_record"}},"created_at":"2026-05-18T00:49:37.182646+00:00","updated_at":"2026-05-18T00:49:37.182646+00:00"}