{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7V56TYUE47EP26GNRV755EMWBT","short_pith_number":"pith:7V56TYUE","schema_version":"1.0","canonical_sha256":"fd7be9e284e7c8fd78cd8d7fde91960cd794fc54bd0249dc06e03efacf0ba72f","source":{"kind":"arxiv","id":"2002.02991","version":1},"attestation_state":"computed","paper":{"title":"Learning Whole-body Motor Skills for Humanoids","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Chuanyu Yang, Kai Yuan, Sethu Vijayakumar, Taku Komura, Wolfgang Merkt, Zhibin Li","submitted_at":"2020-02-07T19:40:59Z","abstract_excerpt":"This paper presents a hierarchical framework for Deep Reinforcement Learning that acquires motor skills for a variety of push recovery and balancing behaviors, i.e., ankle, hip, foot tilting, and stepping strategies. The policy is trained in a physics simulator with realistic setting of robot model and low-level impedance control that are easy to transfer the learned skills to real robots. The advantage over traditional methods is the integration of high-level planner and feedback control all in one single coherent policy network, which is generic for learning versatile balancing and recovery "},"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":"2002.02991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-02-07T19:40:59Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"b05dcf47629d2f26a0634118e99bce6769849d286e314e5a59bbf15a72c27c70","abstract_canon_sha256":"15ef1607ac395b6cc8ebcebe1d0242d2863f0bf48dde8b9fe28cf5bcff50e261"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:17.808035Z","signature_b64":"l6EAYmu1WUEj+aQlC98MRDPxZNt3IlW67e3oIkTUjgrnrNjU4tiMNuwAHPnW1OVtJkcMjdUPLOHvMbN0N4YRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd7be9e284e7c8fd78cd8d7fde91960cd794fc54bd0249dc06e03efacf0ba72f","last_reissued_at":"2026-07-05T00:39:17.807677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:17.807677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Whole-body Motor Skills for Humanoids","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Chuanyu Yang, Kai Yuan, Sethu Vijayakumar, Taku Komura, Wolfgang Merkt, Zhibin Li","submitted_at":"2020-02-07T19:40:59Z","abstract_excerpt":"This paper presents a hierarchical framework for Deep Reinforcement Learning that acquires motor skills for a variety of push recovery and balancing behaviors, i.e., ankle, hip, foot tilting, and stepping strategies. The policy is trained in a physics simulator with realistic setting of robot model and low-level impedance control that are easy to transfer the learned skills to real robots. The advantage over traditional methods is the integration of high-level planner and feedback control all in one single coherent policy network, which is generic for learning versatile balancing and recovery "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02991","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.02991/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2002.02991","created_at":"2026-07-05T00:39:17.807744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.02991v1","created_at":"2026-07-05T00:39:17.807744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02991","created_at":"2026-07-05T00:39:17.807744+00:00"},{"alias_kind":"pith_short_12","alias_value":"7V56TYUE47EP","created_at":"2026-07-05T00:39:17.807744+00:00"},{"alias_kind":"pith_short_16","alias_value":"7V56TYUE47EP26GN","created_at":"2026-07-05T00:39:17.807744+00:00"},{"alias_kind":"pith_short_8","alias_value":"7V56TYUE","created_at":"2026-07-05T00:39:17.807744+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/7V56TYUE47EP26GNRV755EMWBT","json":"https://pith.science/pith/7V56TYUE47EP26GNRV755EMWBT.json","graph_json":"https://pith.science/api/pith-number/7V56TYUE47EP26GNRV755EMWBT/graph.json","events_json":"https://pith.science/api/pith-number/7V56TYUE47EP26GNRV755EMWBT/events.json","paper":"https://pith.science/paper/7V56TYUE"},"agent_actions":{"view_html":"https://pith.science/pith/7V56TYUE47EP26GNRV755EMWBT","download_json":"https://pith.science/pith/7V56TYUE47EP26GNRV755EMWBT.json","view_paper":"https://pith.science/paper/7V56TYUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.02991&json=true","fetch_graph":"https://pith.science/api/pith-number/7V56TYUE47EP26GNRV755EMWBT/graph.json","fetch_events":"https://pith.science/api/pith-number/7V56TYUE47EP26GNRV755EMWBT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7V56TYUE47EP26GNRV755EMWBT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7V56TYUE47EP26GNRV755EMWBT/action/storage_attestation","attest_author":"https://pith.science/pith/7V56TYUE47EP26GNRV755EMWBT/action/author_attestation","sign_citation":"https://pith.science/pith/7V56TYUE47EP26GNRV755EMWBT/action/citation_signature","submit_replication":"https://pith.science/pith/7V56TYUE47EP26GNRV755EMWBT/action/replication_record"}},"created_at":"2026-07-05T00:39:17.807744+00:00","updated_at":"2026-07-05T00:39:17.807744+00:00"}