{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LZRHZY7V5YIQDY6DSG3IBVFTTV","short_pith_number":"pith:LZRHZY7V","schema_version":"1.0","canonical_sha256":"5e627ce3f5ee1101e3c391b680d4b39d6536275fd61da0d907732caafbef2e6e","source":{"kind":"arxiv","id":"2310.05714","version":3},"attestation_state":"computed","paper":{"title":"DecAP: Decaying Action Priors for Accelerated Imitation Learning of Torque-Based Legged Locomotion Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ge Sun, Guillaume Sartoretti, Peizhuo Li, Shivam Sood","submitted_at":"2023-10-09T13:38:03Z","abstract_excerpt":"Optimal Control for legged robots has gone through a paradigm shift from position-based to torque-based control, owing to the latter's compliant and robust nature. In parallel to this shift, the community has also turned to Deep Reinforcement Learning (DRL) as a promising approach to directly learn locomotion policies for complex real-life tasks. However, most end-to-end DRL approaches still operate in position space, mainly because learning in torque space is often sample-inefficient and does not consistently converge to natural gaits. To address these challenges, we propose a two-stage frame"},"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":"2310.05714","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-09T13:38:03Z","cross_cats_sorted":[],"title_canon_sha256":"9e0d2bf1a4a504c69043a20f1a059d74a97cdcc9e783cf3512df30369323dd46","abstract_canon_sha256":"429231fa178ca535cd299086aaa41c14b991ec91548824a69ada857f2956f2c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:26.374244Z","signature_b64":"mL5miHQdg7HmzmwaACNj+GXoMpE4e809lX8Il/Egph2Q7vQegnrO6hYp+Zk52x5bX6IRMSxr0OVVAgtv76FaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e627ce3f5ee1101e3c391b680d4b39d6536275fd61da0d907732caafbef2e6e","last_reissued_at":"2026-07-05T09:01:26.373730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:26.373730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DecAP: Decaying Action Priors for Accelerated Imitation Learning of Torque-Based Legged Locomotion Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ge Sun, Guillaume Sartoretti, Peizhuo Li, Shivam Sood","submitted_at":"2023-10-09T13:38:03Z","abstract_excerpt":"Optimal Control for legged robots has gone through a paradigm shift from position-based to torque-based control, owing to the latter's compliant and robust nature. In parallel to this shift, the community has also turned to Deep Reinforcement Learning (DRL) as a promising approach to directly learn locomotion policies for complex real-life tasks. However, most end-to-end DRL approaches still operate in position space, mainly because learning in torque space is often sample-inefficient and does not consistently converge to natural gaits. To address these challenges, we propose a two-stage frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05714","kind":"arxiv","version":3},"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/2310.05714/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":"2310.05714","created_at":"2026-07-05T09:01:26.373790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05714v3","created_at":"2026-07-05T09:01:26.373790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05714","created_at":"2026-07-05T09:01:26.373790+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZRHZY7V5YIQ","created_at":"2026-07-05T09:01:26.373790+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZRHZY7V5YIQDY6D","created_at":"2026-07-05T09:01:26.373790+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZRHZY7V","created_at":"2026-07-05T09:01:26.373790+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00472","citing_title":"Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZRHZY7V5YIQDY6DSG3IBVFTTV","json":"https://pith.science/pith/LZRHZY7V5YIQDY6DSG3IBVFTTV.json","graph_json":"https://pith.science/api/pith-number/LZRHZY7V5YIQDY6DSG3IBVFTTV/graph.json","events_json":"https://pith.science/api/pith-number/LZRHZY7V5YIQDY6DSG3IBVFTTV/events.json","paper":"https://pith.science/paper/LZRHZY7V"},"agent_actions":{"view_html":"https://pith.science/pith/LZRHZY7V5YIQDY6DSG3IBVFTTV","download_json":"https://pith.science/pith/LZRHZY7V5YIQDY6DSG3IBVFTTV.json","view_paper":"https://pith.science/paper/LZRHZY7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05714&json=true","fetch_graph":"https://pith.science/api/pith-number/LZRHZY7V5YIQDY6DSG3IBVFTTV/graph.json","fetch_events":"https://pith.science/api/pith-number/LZRHZY7V5YIQDY6DSG3IBVFTTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZRHZY7V5YIQDY6DSG3IBVFTTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZRHZY7V5YIQDY6DSG3IBVFTTV/action/storage_attestation","attest_author":"https://pith.science/pith/LZRHZY7V5YIQDY6DSG3IBVFTTV/action/author_attestation","sign_citation":"https://pith.science/pith/LZRHZY7V5YIQDY6DSG3IBVFTTV/action/citation_signature","submit_replication":"https://pith.science/pith/LZRHZY7V5YIQDY6DSG3IBVFTTV/action/replication_record"}},"created_at":"2026-07-05T09:01:26.373790+00:00","updated_at":"2026-07-05T09:01:26.373790+00:00"}