{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5Y53KNO5CVUR7B745SI7QZG75V","short_pith_number":"pith:5Y53KNO5","schema_version":"1.0","canonical_sha256":"ee3bb535dd15691f87fcec91f864dfed4482da7c0eb3d07501b2e02151030c02","source":{"kind":"arxiv","id":"2502.06676","version":1},"attestation_state":"computed","paper":{"title":"Discovery of skill switching criteria for learning agile quadruped locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chuanyu Yang, Dimitrios Kanoulas, Fernando Acero, Ioannis Havoutis, Vassil Atanassov, Wanming Yu, Zhibin Li","submitted_at":"2025-02-10T17:01:03Z","abstract_excerpt":"This paper develops a hierarchical learning and optimization framework that can learn and achieve well-coordinated multi-skill locomotion. The learned multi-skill policy can switch between skills automatically and naturally in tracking arbitrarily positioned goals and recover from failures promptly. The proposed framework is composed of a deep reinforcement learning process and an optimization process. First, the contact pattern is incorporated into the reward terms for learning different types of gaits as separate policies without the need for any other references. Then, a higher level 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":"2502.06676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-10T17:01:03Z","cross_cats_sorted":[],"title_canon_sha256":"17ae820895f2052f5cd53b72e27e2b3939b61a0d3b67b2b55ea82035c230edab","abstract_canon_sha256":"062b490783a26f14d5a40783716e4237eb45425c66d49a81d88bc64355a1803f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:10.464468Z","signature_b64":"bzuQE6Hq0iV102rdZTX/fXALbRwEPo9FtShTFbUcBDjw1Yb5O2hUGKxLSgCWQWos7f1SCF3UHs2c/GjiMUHWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee3bb535dd15691f87fcec91f864dfed4482da7c0eb3d07501b2e02151030c02","last_reissued_at":"2026-07-05T10:12:10.463817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:10.463817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discovery of skill switching criteria for learning agile quadruped locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chuanyu Yang, Dimitrios Kanoulas, Fernando Acero, Ioannis Havoutis, Vassil Atanassov, Wanming Yu, Zhibin Li","submitted_at":"2025-02-10T17:01:03Z","abstract_excerpt":"This paper develops a hierarchical learning and optimization framework that can learn and achieve well-coordinated multi-skill locomotion. The learned multi-skill policy can switch between skills automatically and naturally in tracking arbitrarily positioned goals and recover from failures promptly. The proposed framework is composed of a deep reinforcement learning process and an optimization process. First, the contact pattern is incorporated into the reward terms for learning different types of gaits as separate policies without the need for any other references. Then, a higher level policy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06676","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/2502.06676/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":"2502.06676","created_at":"2026-07-05T10:12:10.463910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06676v1","created_at":"2026-07-05T10:12:10.463910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06676","created_at":"2026-07-05T10:12:10.463910+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Y53KNO5CVUR","created_at":"2026-07-05T10:12:10.463910+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Y53KNO5CVUR7B74","created_at":"2026-07-05T10:12:10.463910+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Y53KNO5","created_at":"2026-07-05T10:12:10.463910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.18780","citing_title":"DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13058","citing_title":"MUJICA: Multi-skill Unified Joint Integration of Control Architecture for Wheeled-Legged Robots","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Y53KNO5CVUR7B745SI7QZG75V","json":"https://pith.science/pith/5Y53KNO5CVUR7B745SI7QZG75V.json","graph_json":"https://pith.science/api/pith-number/5Y53KNO5CVUR7B745SI7QZG75V/graph.json","events_json":"https://pith.science/api/pith-number/5Y53KNO5CVUR7B745SI7QZG75V/events.json","paper":"https://pith.science/paper/5Y53KNO5"},"agent_actions":{"view_html":"https://pith.science/pith/5Y53KNO5CVUR7B745SI7QZG75V","download_json":"https://pith.science/pith/5Y53KNO5CVUR7B745SI7QZG75V.json","view_paper":"https://pith.science/paper/5Y53KNO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06676&json=true","fetch_graph":"https://pith.science/api/pith-number/5Y53KNO5CVUR7B745SI7QZG75V/graph.json","fetch_events":"https://pith.science/api/pith-number/5Y53KNO5CVUR7B745SI7QZG75V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Y53KNO5CVUR7B745SI7QZG75V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Y53KNO5CVUR7B745SI7QZG75V/action/storage_attestation","attest_author":"https://pith.science/pith/5Y53KNO5CVUR7B745SI7QZG75V/action/author_attestation","sign_citation":"https://pith.science/pith/5Y53KNO5CVUR7B745SI7QZG75V/action/citation_signature","submit_replication":"https://pith.science/pith/5Y53KNO5CVUR7B745SI7QZG75V/action/replication_record"}},"created_at":"2026-07-05T10:12:10.463910+00:00","updated_at":"2026-07-05T10:12:10.463910+00:00"}