{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OCPVRAVHI3EV3MCDVHOT4JBETK","short_pith_number":"pith:OCPVRAVH","schema_version":"1.0","canonical_sha256":"709f5882a746c95db043a9dd3e24249ab8f7789bdaeda05ac10f4a62602f2d4c","source":{"kind":"arxiv","id":"1710.00022","version":2},"attestation_state":"computed","paper":{"title":"Learning a Structured Neural Network Policy for a Hopping Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alexander Herzog, Jules Kozolinsky, Julian Viereck, Ludovic Righetti","submitted_at":"2017-09-29T18:35:54Z","abstract_excerpt":"In this work we present a method for learning a reactive policy for a simple dynamic locomotion task involving hard impact and switching contacts where we assume the contact location and contact timing to be unknown. To learn such a policy, we use optimal control to optimize a local controller for a fixed environment and contacts. We learn the contact-rich dynamics for our underactuated systems along these trajectories in a sample efficient manner. We use the optimized policies to learn the reactive policy in form of a neural network. Using a new neural network architecture, we are able to pre"},"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":"1710.00022","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-29T18:35:54Z","cross_cats_sorted":[],"title_canon_sha256":"647f435de683c902d88b6cd06e654287c292379a8a0ef1aaa5763e60a7d9cdab","abstract_canon_sha256":"c67fbc9c108c3fdcc3eeb72415a75fd047dd0a9e61c69310b0fdefd5a657883b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:55.093011Z","signature_b64":"158TOLmQq+sat4EFC/6HI1O9fBnvgcFMERTXsIsaRvpI7tELwIdbIcmk6vn33f+mU1HQIO3p7zOnCUK1s5OMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"709f5882a746c95db043a9dd3e24249ab8f7789bdaeda05ac10f4a62602f2d4c","last_reissued_at":"2026-05-18T00:08:55.092524Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:55.092524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Structured Neural Network Policy for a Hopping Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alexander Herzog, Jules Kozolinsky, Julian Viereck, Ludovic Righetti","submitted_at":"2017-09-29T18:35:54Z","abstract_excerpt":"In this work we present a method for learning a reactive policy for a simple dynamic locomotion task involving hard impact and switching contacts where we assume the contact location and contact timing to be unknown. To learn such a policy, we use optimal control to optimize a local controller for a fixed environment and contacts. We learn the contact-rich dynamics for our underactuated systems along these trajectories in a sample efficient manner. We use the optimized policies to learn the reactive policy in form of a neural network. Using a new neural network architecture, we are able to pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00022","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":"1710.00022","created_at":"2026-05-18T00:08:55.092595+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.00022v2","created_at":"2026-05-18T00:08:55.092595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00022","created_at":"2026-05-18T00:08:55.092595+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCPVRAVHI3EV","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCPVRAVHI3EV3MCD","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCPVRAVH","created_at":"2026-05-18T12:31:34.259226+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/OCPVRAVHI3EV3MCDVHOT4JBETK","json":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK.json","graph_json":"https://pith.science/api/pith-number/OCPVRAVHI3EV3MCDVHOT4JBETK/graph.json","events_json":"https://pith.science/api/pith-number/OCPVRAVHI3EV3MCDVHOT4JBETK/events.json","paper":"https://pith.science/paper/OCPVRAVH"},"agent_actions":{"view_html":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK","download_json":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK.json","view_paper":"https://pith.science/paper/OCPVRAVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.00022&json=true","fetch_graph":"https://pith.science/api/pith-number/OCPVRAVHI3EV3MCDVHOT4JBETK/graph.json","fetch_events":"https://pith.science/api/pith-number/OCPVRAVHI3EV3MCDVHOT4JBETK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK/action/storage_attestation","attest_author":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK/action/author_attestation","sign_citation":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK/action/citation_signature","submit_replication":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK/action/replication_record"}},"created_at":"2026-05-18T00:08:55.092595+00:00","updated_at":"2026-05-18T00:08:55.092595+00:00"}