{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P4UESQFWMOXSVP4IYGLMQA22YV","short_pith_number":"pith:P4UESQFW","schema_version":"1.0","canonical_sha256":"7f284940b663af2abf88c196c8035ac54863e76e8e5179da56abec56f822eeee","source":{"kind":"arxiv","id":"2311.10484","version":2},"attestation_state":"computed","paper":{"title":"Learning Agile Locomotion on Risky Terrains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chong Zhang, David Hoeller, Marco Hutter, Nikita Rudin","submitted_at":"2023-11-17T12:32:57Z","abstract_excerpt":"Quadruped robots have shown remarkable mobility on various terrains through reinforcement learning. Yet, in the presence of sparse footholds and risky terrains such as stepping stones and balance beams, which require precise foot placement to avoid falls, model-based approaches are often used. In this paper, we show that end-to-end reinforcement learning can also enable the robot to traverse risky terrains with dynamic motions. To this end, our approach involves training a generalist policy for agile locomotion on disorderly and sparse stepping stones before transferring its reusable knowledge"},"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":"2311.10484","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-17T12:32:57Z","cross_cats_sorted":[],"title_canon_sha256":"bcc83a9c25600d8b9451f729b279fe392236638a1193e690fd4da489895e517b","abstract_canon_sha256":"237ba9832c7674bb49d371fcc142e2d297e171b658ad0186ac96c1b8b5431932"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:38.338050Z","signature_b64":"vNPzPoK/h/skVji5inj4i/d21bFzm5JPOMCBPRxdPjC+Zqo5TZ/U8yCW9sRpIoYaccjpK8RD1n1A+0PoJx+5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f284940b663af2abf88c196c8035ac54863e76e8e5179da56abec56f822eeee","last_reissued_at":"2026-07-05T08:53:38.337577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:38.337577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Agile Locomotion on Risky Terrains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chong Zhang, David Hoeller, Marco Hutter, Nikita Rudin","submitted_at":"2023-11-17T12:32:57Z","abstract_excerpt":"Quadruped robots have shown remarkable mobility on various terrains through reinforcement learning. Yet, in the presence of sparse footholds and risky terrains such as stepping stones and balance beams, which require precise foot placement to avoid falls, model-based approaches are often used. In this paper, we show that end-to-end reinforcement learning can also enable the robot to traverse risky terrains with dynamic motions. To this end, our approach involves training a generalist policy for agile locomotion on disorderly and sparse stepping stones before transferring its reusable knowledge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10484","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/2311.10484/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":"2311.10484","created_at":"2026-07-05T08:53:38.337634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10484v2","created_at":"2026-07-05T08:53:38.337634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10484","created_at":"2026-07-05T08:53:38.337634+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4UESQFWMOXS","created_at":"2026-07-05T08:53:38.337634+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4UESQFWMOXSVP4I","created_at":"2026-07-05T08:53:38.337634+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4UESQFW","created_at":"2026-07-05T08:53:38.337634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.03599","citing_title":"Learning to Act Through Contact: A Unified View of Multi-Task Robot Learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02744","citing_title":"Learning Locomotion on Complex Terrain for Quadrupedal Robots with Foot Position Maps and Stability Rewards","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4UESQFWMOXSVP4IYGLMQA22YV","json":"https://pith.science/pith/P4UESQFWMOXSVP4IYGLMQA22YV.json","graph_json":"https://pith.science/api/pith-number/P4UESQFWMOXSVP4IYGLMQA22YV/graph.json","events_json":"https://pith.science/api/pith-number/P4UESQFWMOXSVP4IYGLMQA22YV/events.json","paper":"https://pith.science/paper/P4UESQFW"},"agent_actions":{"view_html":"https://pith.science/pith/P4UESQFWMOXSVP4IYGLMQA22YV","download_json":"https://pith.science/pith/P4UESQFWMOXSVP4IYGLMQA22YV.json","view_paper":"https://pith.science/paper/P4UESQFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10484&json=true","fetch_graph":"https://pith.science/api/pith-number/P4UESQFWMOXSVP4IYGLMQA22YV/graph.json","fetch_events":"https://pith.science/api/pith-number/P4UESQFWMOXSVP4IYGLMQA22YV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4UESQFWMOXSVP4IYGLMQA22YV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4UESQFWMOXSVP4IYGLMQA22YV/action/storage_attestation","attest_author":"https://pith.science/pith/P4UESQFWMOXSVP4IYGLMQA22YV/action/author_attestation","sign_citation":"https://pith.science/pith/P4UESQFWMOXSVP4IYGLMQA22YV/action/citation_signature","submit_replication":"https://pith.science/pith/P4UESQFWMOXSVP4IYGLMQA22YV/action/replication_record"}},"created_at":"2026-07-05T08:53:38.337634+00:00","updated_at":"2026-07-05T08:53:38.337634+00:00"}