{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H7JWLBVJALVFE2J47EQZ22PVIJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f46411f38bc481b3b9066743608c137245a2c9353defa8f58f8a821263a8b71a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-01-23T01:17:07Z","title_canon_sha256":"3828cdb56d30fdd2893b40fbf8f1d525467626ab6d2418cbadc051c28eebb2ab"},"schema_version":"1.0","source":{"id":"2101.09391","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.09391","created_at":"2026-07-05T05:03:48Z"},{"alias_kind":"arxiv_version","alias_value":"2101.09391v2","created_at":"2026-07-05T05:03:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09391","created_at":"2026-07-05T05:03:48Z"},{"alias_kind":"pith_short_12","alias_value":"H7JWLBVJALVF","created_at":"2026-07-05T05:03:48Z"},{"alias_kind":"pith_short_16","alias_value":"H7JWLBVJALVFE2J4","created_at":"2026-07-05T05:03:48Z"},{"alias_kind":"pith_short_8","alias_value":"H7JWLBVJ","created_at":"2026-07-05T05:03:48Z"}],"graph_snapshots":[{"event_id":"sha256:ad02ed0f639a0891ace436c8fe15e3083d43cf5986e3304bdc03278763ecacca","target":"graph","created_at":"2026-07-05T05:03:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2101.09391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Akansel Cosgun, Brendan Tidd, Jurgen Leitner, Nicolas Hudson","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-01-23T01:17:07Z","title":"Learning Setup Policies: Reliable Transition Between Locomotion Behaviours"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09391","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:71e859c38342726413e8e57f45fa803ad132c08228087c0446e8d9fda3213bd4","target":"record","created_at":"2026-07-05T05:03:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f46411f38bc481b3b9066743608c137245a2c9353defa8f58f8a821263a8b71a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-01-23T01:17:07Z","title_canon_sha256":"3828cdb56d30fdd2893b40fbf8f1d525467626ab6d2418cbadc051c28eebb2ab"},"schema_version":"1.0","source":{"id":"2101.09391","kind":"arxiv","version":2}},"canonical_sha256":"3fd36586a902ea52693cf9219d69f5424786648e263feeadf19092737249d9db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fd36586a902ea52693cf9219d69f5424786648e263feeadf19092737249d9db","first_computed_at":"2026-07-05T05:03:48.859626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:48.859626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pLaOdvXZJJCiZ0suCph7IbY26Y5EGeiOKTd5UB5yTyUuuOkx5Br1iU64aoT8PeEI67ivQdio9GMOAArGgrCNDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:48.860056Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.09391","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71e859c38342726413e8e57f45fa803ad132c08228087c0446e8d9fda3213bd4","sha256:ad02ed0f639a0891ace436c8fe15e3083d43cf5986e3304bdc03278763ecacca"],"state_sha256":"7391f841fd48698fccf476af945fce9ede00a681fc2970b50a90f7719b6e5f51"}