{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PRSXVSXGI7ESN3T42YJOAY7LWI","short_pith_number":"pith:PRSXVSXG","schema_version":"1.0","canonical_sha256":"7c657acae647c926ee7cd612e063ebb2089e747ad92d4cb7babeda6b76d0f06e","source":{"kind":"arxiv","id":"2403.01962","version":2},"attestation_state":"computed","paper":{"title":"An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haojie Shi, Jiapeng sheng, Lei Han, Max Q.-H. Meng, Qingxu Zhu, Tingguang Li","submitted_at":"2024-03-04T12:01:11Z","abstract_excerpt":"Learning-based methods have improved locomotion skills of quadruped robots through deep reinforcement learning. However, the sim-to-real gap and low sample efficiency still limit the skill transfer. To address this issue, we propose an efficient model-based learning framework that combines a world model with a policy network. We train a differentiable world model to predict future states and use it to directly supervise a Variational Autoencoder (VAE)-based policy network to imitate real animal behaviors. This significantly reduces the need for real interaction data and allows for rapid policy"},"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":"2403.01962","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-04T12:01:11Z","cross_cats_sorted":[],"title_canon_sha256":"4ee8536567c3fc55adb8c9648c749ce3aa79a69c27dd5bea871d29776f6988c8","abstract_canon_sha256":"c1ce3f413f3969d03dca817ebc8564a3b34d25800fa216102e444bef55ebd265"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:00.669106Z","signature_b64":"wryXSzRGUvU75rgbEY2SjwB3jfWizNSDFhsTnHXd+OKBQiFGlQdMjXR6R3oERlTObKTr6aPuomqI2cH9oTeMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c657acae647c926ee7cd612e063ebb2089e747ad92d4cb7babeda6b76d0f06e","last_reissued_at":"2026-07-05T07:57:00.668596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:00.668596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haojie Shi, Jiapeng sheng, Lei Han, Max Q.-H. Meng, Qingxu Zhu, Tingguang Li","submitted_at":"2024-03-04T12:01:11Z","abstract_excerpt":"Learning-based methods have improved locomotion skills of quadruped robots through deep reinforcement learning. However, the sim-to-real gap and low sample efficiency still limit the skill transfer. To address this issue, we propose an efficient model-based learning framework that combines a world model with a policy network. We train a differentiable world model to predict future states and use it to directly supervise a Variational Autoencoder (VAE)-based policy network to imitate real animal behaviors. This significantly reduces the need for real interaction data and allows for rapid policy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01962","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.01962/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":"2403.01962","created_at":"2026-07-05T07:57:00.668656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01962v2","created_at":"2026-07-05T07:57:00.668656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01962","created_at":"2026-07-05T07:57:00.668656+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRSXVSXGI7ES","created_at":"2026-07-05T07:57:00.668656+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRSXVSXGI7ESN3T4","created_at":"2026-07-05T07:57:00.668656+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRSXVSXG","created_at":"2026-07-05T07:57:00.668656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24592","citing_title":"MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRSXVSXGI7ESN3T42YJOAY7LWI","json":"https://pith.science/pith/PRSXVSXGI7ESN3T42YJOAY7LWI.json","graph_json":"https://pith.science/api/pith-number/PRSXVSXGI7ESN3T42YJOAY7LWI/graph.json","events_json":"https://pith.science/api/pith-number/PRSXVSXGI7ESN3T42YJOAY7LWI/events.json","paper":"https://pith.science/paper/PRSXVSXG"},"agent_actions":{"view_html":"https://pith.science/pith/PRSXVSXGI7ESN3T42YJOAY7LWI","download_json":"https://pith.science/pith/PRSXVSXGI7ESN3T42YJOAY7LWI.json","view_paper":"https://pith.science/paper/PRSXVSXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01962&json=true","fetch_graph":"https://pith.science/api/pith-number/PRSXVSXGI7ESN3T42YJOAY7LWI/graph.json","fetch_events":"https://pith.science/api/pith-number/PRSXVSXGI7ESN3T42YJOAY7LWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRSXVSXGI7ESN3T42YJOAY7LWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRSXVSXGI7ESN3T42YJOAY7LWI/action/storage_attestation","attest_author":"https://pith.science/pith/PRSXVSXGI7ESN3T42YJOAY7LWI/action/author_attestation","sign_citation":"https://pith.science/pith/PRSXVSXGI7ESN3T42YJOAY7LWI/action/citation_signature","submit_replication":"https://pith.science/pith/PRSXVSXGI7ESN3T42YJOAY7LWI/action/replication_record"}},"created_at":"2026-07-05T07:57:00.668656+00:00","updated_at":"2026-07-05T07:57:00.668656+00:00"}