{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ABRTB56LEXROXD7CLUWGB7CGXH","short_pith_number":"pith:ABRTB56L","schema_version":"1.0","canonical_sha256":"006330f7cb25e2eb8fe25d2c60fc46b9f1b4c7dda82903033e2edaad6bf9d586","source":{"kind":"arxiv","id":"2111.13129","version":2},"attestation_state":"computed","paper":{"title":"Robot Skill Adaptation via Soft Actor-Critic Gaussian Mixture Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abhinav Valada, Adrian R\\\"ofer, Erick Rosete-Beas, Iman Nematollahi, Tim Welschehold, Wolfram Burgard","submitted_at":"2021-11-25T15:36:11Z","abstract_excerpt":"A core challenge for an autonomous agent acting in the real world is to adapt its repertoire of skills to cope with its noisy perception and dynamics. To scale learning of skills to long-horizon tasks, robots should be able to learn and later refine their skills in a structured manner through trajectories rather than making instantaneous decisions individually at each time step. To this end, we propose the Soft Actor-Critic Gaussian Mixture Model (SAC-GMM), a novel hybrid approach that learns robot skills through a dynamical system and adapts the learned skills in their own trajectory distribu"},"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":"2111.13129","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-25T15:36:11Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"bd16109a9e49d4eb65f349b04b88f58599e765e4b11dd473fb4647c16a3430ab","abstract_canon_sha256":"8d18e35073a3b8bfdabe607dee58ef679ad16bb5017efab914c002a6b78e287a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:33.437253Z","signature_b64":"uH5qPkK4Pntj7IzThBT8dtqJnYnunNyGHgHiWDFK0qT5LjZvFC6kyr43b0d4vr1CpI8+3jDUGBoTAZFNTy82BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"006330f7cb25e2eb8fe25d2c60fc46b9f1b4c7dda82903033e2edaad6bf9d586","last_reissued_at":"2026-07-05T04:58:33.436750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:33.436750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robot Skill Adaptation via Soft Actor-Critic Gaussian Mixture Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abhinav Valada, Adrian R\\\"ofer, Erick Rosete-Beas, Iman Nematollahi, Tim Welschehold, Wolfram Burgard","submitted_at":"2021-11-25T15:36:11Z","abstract_excerpt":"A core challenge for an autonomous agent acting in the real world is to adapt its repertoire of skills to cope with its noisy perception and dynamics. To scale learning of skills to long-horizon tasks, robots should be able to learn and later refine their skills in a structured manner through trajectories rather than making instantaneous decisions individually at each time step. To this end, we propose the Soft Actor-Critic Gaussian Mixture Model (SAC-GMM), a novel hybrid approach that learns robot skills through a dynamical system and adapts the learned skills in their own trajectory distribu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13129","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/2111.13129/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":"2111.13129","created_at":"2026-07-05T04:58:33.436812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13129v2","created_at":"2026-07-05T04:58:33.436812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13129","created_at":"2026-07-05T04:58:33.436812+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABRTB56LEXRO","created_at":"2026-07-05T04:58:33.436812+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABRTB56LEXROXD7C","created_at":"2026-07-05T04:58:33.436812+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABRTB56L","created_at":"2026-07-05T04:58:33.436812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05084","citing_title":"Learning When to Stop: Prefix-Optimal Dynamic Diffusion Policies for Continuous Control","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ABRTB56LEXROXD7CLUWGB7CGXH","json":"https://pith.science/pith/ABRTB56LEXROXD7CLUWGB7CGXH.json","graph_json":"https://pith.science/api/pith-number/ABRTB56LEXROXD7CLUWGB7CGXH/graph.json","events_json":"https://pith.science/api/pith-number/ABRTB56LEXROXD7CLUWGB7CGXH/events.json","paper":"https://pith.science/paper/ABRTB56L"},"agent_actions":{"view_html":"https://pith.science/pith/ABRTB56LEXROXD7CLUWGB7CGXH","download_json":"https://pith.science/pith/ABRTB56LEXROXD7CLUWGB7CGXH.json","view_paper":"https://pith.science/paper/ABRTB56L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13129&json=true","fetch_graph":"https://pith.science/api/pith-number/ABRTB56LEXROXD7CLUWGB7CGXH/graph.json","fetch_events":"https://pith.science/api/pith-number/ABRTB56LEXROXD7CLUWGB7CGXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABRTB56LEXROXD7CLUWGB7CGXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABRTB56LEXROXD7CLUWGB7CGXH/action/storage_attestation","attest_author":"https://pith.science/pith/ABRTB56LEXROXD7CLUWGB7CGXH/action/author_attestation","sign_citation":"https://pith.science/pith/ABRTB56LEXROXD7CLUWGB7CGXH/action/citation_signature","submit_replication":"https://pith.science/pith/ABRTB56LEXROXD7CLUWGB7CGXH/action/replication_record"}},"created_at":"2026-07-05T04:58:33.436812+00:00","updated_at":"2026-07-05T04:58:33.436812+00:00"}