{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:H7JWLBVJALVFE2J47EQZ22PVIJ","short_pith_number":"pith:H7JWLBVJ","schema_version":"1.0","canonical_sha256":"3fd36586a902ea52693cf9219d69f5424786648e263feeadf19092737249d9db","source":{"kind":"arxiv","id":"2101.09391","version":2},"attestation_state":"computed","paper":{"title":"Learning Setup Policies: Reliable Transition Between Locomotion Behaviours","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Akansel Cosgun, Brendan Tidd, Jurgen Leitner, Nicolas Hudson","submitted_at":"2021-01-23T01:17:07Z","abstract_excerpt":"Dynamic platforms that operate over many unique terrain conditions typically require many behaviours. To transition safely, there must be an overlap of states between adjacent controllers. We develop a novel method for training setup policies that bridge the trajectories between pre-trained Deep Reinforcement Learning (DRL) policies. We demonstrate our method with a simulated biped traversing a difficult jump terrain, where a single policy fails to learn the task, and switching between pre-trained policies without setup policies also fails. We perform an ablation of key components of our syste"},"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":"2101.09391","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-01-23T01:17:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3828cdb56d30fdd2893b40fbf8f1d525467626ab6d2418cbadc051c28eebb2ab","abstract_canon_sha256":"f46411f38bc481b3b9066743608c137245a2c9353defa8f58f8a821263a8b71a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:48.860056Z","signature_b64":"pLaOdvXZJJCiZ0suCph7IbY26Y5EGeiOKTd5UB5yTyUuuOkx5Br1iU64aoT8PeEI67ivQdio9GMOAArGgrCNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fd36586a902ea52693cf9219d69f5424786648e263feeadf19092737249d9db","last_reissued_at":"2026-07-05T05:03:48.859626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:48.859626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Setup Policies: Reliable Transition Between Locomotion Behaviours","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Akansel Cosgun, Brendan Tidd, Jurgen Leitner, Nicolas Hudson","submitted_at":"2021-01-23T01:17:07Z","abstract_excerpt":"Dynamic platforms that operate over many unique terrain conditions typically require many behaviours. To transition safely, there must be an overlap of states between adjacent controllers. We develop a novel method for training setup policies that bridge the trajectories between pre-trained Deep Reinforcement Learning (DRL) policies. We demonstrate our method with a simulated biped traversing a difficult jump terrain, where a single policy fails to learn the task, and switching between pre-trained policies without setup policies also fails. We perform an ablation of key components of our syste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09391","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/2101.09391/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":"2101.09391","created_at":"2026-07-05T05:03:48.859683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.09391v2","created_at":"2026-07-05T05:03:48.859683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09391","created_at":"2026-07-05T05:03:48.859683+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7JWLBVJALVF","created_at":"2026-07-05T05:03:48.859683+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7JWLBVJALVFE2J4","created_at":"2026-07-05T05:03:48.859683+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7JWLBVJ","created_at":"2026-07-05T05:03:48.859683+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/H7JWLBVJALVFE2J47EQZ22PVIJ","json":"https://pith.science/pith/H7JWLBVJALVFE2J47EQZ22PVIJ.json","graph_json":"https://pith.science/api/pith-number/H7JWLBVJALVFE2J47EQZ22PVIJ/graph.json","events_json":"https://pith.science/api/pith-number/H7JWLBVJALVFE2J47EQZ22PVIJ/events.json","paper":"https://pith.science/paper/H7JWLBVJ"},"agent_actions":{"view_html":"https://pith.science/pith/H7JWLBVJALVFE2J47EQZ22PVIJ","download_json":"https://pith.science/pith/H7JWLBVJALVFE2J47EQZ22PVIJ.json","view_paper":"https://pith.science/paper/H7JWLBVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.09391&json=true","fetch_graph":"https://pith.science/api/pith-number/H7JWLBVJALVFE2J47EQZ22PVIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/H7JWLBVJALVFE2J47EQZ22PVIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7JWLBVJALVFE2J47EQZ22PVIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7JWLBVJALVFE2J47EQZ22PVIJ/action/storage_attestation","attest_author":"https://pith.science/pith/H7JWLBVJALVFE2J47EQZ22PVIJ/action/author_attestation","sign_citation":"https://pith.science/pith/H7JWLBVJALVFE2J47EQZ22PVIJ/action/citation_signature","submit_replication":"https://pith.science/pith/H7JWLBVJALVFE2J47EQZ22PVIJ/action/replication_record"}},"created_at":"2026-07-05T05:03:48.859683+00:00","updated_at":"2026-07-05T05:03:48.859683+00:00"}