{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HBWQGY5OS3TQLE34MT5ABOQLK4","short_pith_number":"pith:HBWQGY5O","schema_version":"1.0","canonical_sha256":"386d0363ae96e705937c64fa00ba0b570ac8cac8f5f97d2a70d584dffc732872","source":{"kind":"arxiv","id":"1706.09597","version":1},"attestation_state":"computed","paper":{"title":"Path Integral Networks: End-to-End Differentiable Optimal Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"cs.AI","authors_text":"Luca Rigazio, Masashi Okada, Takenobu Aoshima","submitted_at":"2017-06-29T07:13:15Z","abstract_excerpt":"In this paper, we introduce Path Integral Networks (PI-Net), a recurrent network representation of the Path Integral optimal control algorithm. The network includes both system dynamics and cost models, used for optimal control based planning. PI-Net is fully differentiable, learning both dynamics and cost models end-to-end by back-propagation and stochastic gradient descent. Because of this, PI-Net can learn to plan. PI-Net has several advantages: it can generalize to unseen states thanks to planning, it can be applied to continuous control tasks, and it allows for a wide variety learning sch"},"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":"1706.09597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-29T07:13:15Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"18220842ebf62a63f6353fa63c631c4b35488a1c1bb4ecc15f504b6066134d15","abstract_canon_sha256":"91b5541b4f2a5c3479e8752c4eec816ce2bcb11ca800f4a8bcecfc411190d02a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:14.468142Z","signature_b64":"ekSI98A6YMGBUvBdI6egsGo+9m/hghiIUIzlVgV9pRlK2B5N3IRq94QKbDhQ1uFH/OYt4oUs+hfMxJLqXu0oBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"386d0363ae96e705937c64fa00ba0b570ac8cac8f5f97d2a70d584dffc732872","last_reissued_at":"2026-05-18T00:41:14.467573Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:14.467573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Path Integral Networks: End-to-End Differentiable Optimal Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"cs.AI","authors_text":"Luca Rigazio, Masashi Okada, Takenobu Aoshima","submitted_at":"2017-06-29T07:13:15Z","abstract_excerpt":"In this paper, we introduce Path Integral Networks (PI-Net), a recurrent network representation of the Path Integral optimal control algorithm. The network includes both system dynamics and cost models, used for optimal control based planning. PI-Net is fully differentiable, learning both dynamics and cost models end-to-end by back-propagation and stochastic gradient descent. Because of this, PI-Net can learn to plan. PI-Net has several advantages: it can generalize to unseen states thanks to planning, it can be applied to continuous control tasks, and it allows for a wide variety learning sch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.09597","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":"1706.09597","created_at":"2026-05-18T00:41:14.467654+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.09597v1","created_at":"2026-05-18T00:41:14.467654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.09597","created_at":"2026-05-18T00:41:14.467654+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBWQGY5OS3TQ","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBWQGY5OS3TQLE34","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBWQGY5O","created_at":"2026-05-18T12:31:18.294218+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/HBWQGY5OS3TQLE34MT5ABOQLK4","json":"https://pith.science/pith/HBWQGY5OS3TQLE34MT5ABOQLK4.json","graph_json":"https://pith.science/api/pith-number/HBWQGY5OS3TQLE34MT5ABOQLK4/graph.json","events_json":"https://pith.science/api/pith-number/HBWQGY5OS3TQLE34MT5ABOQLK4/events.json","paper":"https://pith.science/paper/HBWQGY5O"},"agent_actions":{"view_html":"https://pith.science/pith/HBWQGY5OS3TQLE34MT5ABOQLK4","download_json":"https://pith.science/pith/HBWQGY5OS3TQLE34MT5ABOQLK4.json","view_paper":"https://pith.science/paper/HBWQGY5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.09597&json=true","fetch_graph":"https://pith.science/api/pith-number/HBWQGY5OS3TQLE34MT5ABOQLK4/graph.json","fetch_events":"https://pith.science/api/pith-number/HBWQGY5OS3TQLE34MT5ABOQLK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBWQGY5OS3TQLE34MT5ABOQLK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBWQGY5OS3TQLE34MT5ABOQLK4/action/storage_attestation","attest_author":"https://pith.science/pith/HBWQGY5OS3TQLE34MT5ABOQLK4/action/author_attestation","sign_citation":"https://pith.science/pith/HBWQGY5OS3TQLE34MT5ABOQLK4/action/citation_signature","submit_replication":"https://pith.science/pith/HBWQGY5OS3TQLE34MT5ABOQLK4/action/replication_record"}},"created_at":"2026-05-18T00:41:14.467654+00:00","updated_at":"2026-05-18T00:41:14.467654+00:00"}