{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7Q2DJTV5C22UQ43LTVLSUMMOX2","short_pith_number":"pith:7Q2DJTV5","schema_version":"1.0","canonical_sha256":"fc3434cebd16b548736b9d572a318ebe83cb5b9682c7ef72bd6070d5dfa0e40c","source":{"kind":"arxiv","id":"2510.12363","version":4},"attestation_state":"computed","paper":{"title":"Pretraining in Actor-Critic Reinforcement Learning for Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrei Cramariuc, Jiale Fan, Marco Hutter, Tifanny Portela","submitted_at":"2025-10-14T10:25:40Z","abstract_excerpt":"The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years. However, in the domain of reinforcement learning (RL) for robot locomotion, individual skills are often learned from scratch despite the high likelihood that some generalizable knowledge is shared across all task-specific policies belonging to the same robot embodiment. This work aims to define a paradigm for pretraining neural network models that encapsulate such knowledge and can subsequently serve as a basis for warm-starting the RL process in classic"},"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":"2510.12363","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-10-14T10:25:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a48decaebe2db45c0f1c91aa2108d08087c59f6f18fe65daccc6b346f4a7aa14","abstract_canon_sha256":"f7f61e2755e92bab8694e4e9a2bc3b0f8f0e27472c2447fa377bc4c38d6d40cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:28.757988Z","signature_b64":"R0a2gvRLQFIH9lJ5R1jhNAGgXShUURf6Qf9XsegueQn0k3MYpdiUYT5/SygAAaT8X6VtSBg1uW86M+1oPQTRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc3434cebd16b548736b9d572a318ebe83cb5b9682c7ef72bd6070d5dfa0e40c","last_reissued_at":"2026-07-16T01:22:28.757099Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:28.757099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pretraining in Actor-Critic Reinforcement Learning for Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrei Cramariuc, Jiale Fan, Marco Hutter, Tifanny Portela","submitted_at":"2025-10-14T10:25:40Z","abstract_excerpt":"The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years. However, in the domain of reinforcement learning (RL) for robot locomotion, individual skills are often learned from scratch despite the high likelihood that some generalizable knowledge is shared across all task-specific policies belonging to the same robot embodiment. This work aims to define a paradigm for pretraining neural network models that encapsulate such knowledge and can subsequently serve as a basis for warm-starting the RL process in classic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.12363","kind":"arxiv","version":4},"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/2510.12363/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":"2510.12363","created_at":"2026-07-16T01:22:28.757518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.12363v4","created_at":"2026-07-16T01:22:28.757518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.12363","created_at":"2026-07-16T01:22:28.757518+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Q2DJTV5C22U","created_at":"2026-07-16T01:22:28.757518+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Q2DJTV5C22UQ43L","created_at":"2026-07-16T01:22:28.757518+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Q2DJTV5","created_at":"2026-07-16T01:22:28.757518+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/7Q2DJTV5C22UQ43LTVLSUMMOX2","json":"https://pith.science/pith/7Q2DJTV5C22UQ43LTVLSUMMOX2.json","graph_json":"https://pith.science/api/pith-number/7Q2DJTV5C22UQ43LTVLSUMMOX2/graph.json","events_json":"https://pith.science/api/pith-number/7Q2DJTV5C22UQ43LTVLSUMMOX2/events.json","paper":"https://pith.science/paper/7Q2DJTV5"},"agent_actions":{"view_html":"https://pith.science/pith/7Q2DJTV5C22UQ43LTVLSUMMOX2","download_json":"https://pith.science/pith/7Q2DJTV5C22UQ43LTVLSUMMOX2.json","view_paper":"https://pith.science/paper/7Q2DJTV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.12363&json=true","fetch_graph":"https://pith.science/api/pith-number/7Q2DJTV5C22UQ43LTVLSUMMOX2/graph.json","fetch_events":"https://pith.science/api/pith-number/7Q2DJTV5C22UQ43LTVLSUMMOX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Q2DJTV5C22UQ43LTVLSUMMOX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Q2DJTV5C22UQ43LTVLSUMMOX2/action/storage_attestation","attest_author":"https://pith.science/pith/7Q2DJTV5C22UQ43LTVLSUMMOX2/action/author_attestation","sign_citation":"https://pith.science/pith/7Q2DJTV5C22UQ43LTVLSUMMOX2/action/citation_signature","submit_replication":"https://pith.science/pith/7Q2DJTV5C22UQ43LTVLSUMMOX2/action/replication_record"}},"created_at":"2026-07-16T01:22:28.757518+00:00","updated_at":"2026-07-16T01:22:28.757518+00:00"}