{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ERBCMH5TWDRSTBPNIEIKMPJ4CL","short_pith_number":"pith:ERBCMH5T","schema_version":"1.0","canonical_sha256":"2442261fb3b0e32985ed4110a63d3c12d5c328b3a7a3c1a79eb5155910945c7e","source":{"kind":"arxiv","id":"2010.08252","version":4},"attestation_state":"computed","paper":{"title":"Hyperparameter Auto-tuning in Self-Supervised Robotic Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Hongmin Wu, Jiancong Huang, Juan Rojas, Matthieu Zimmer, Paul Weng, Yisheng Guan","submitted_at":"2020-10-16T08:58:24Z","abstract_excerpt":"Policy optimization in reinforcement learning requires the selection of numerous hyperparameters across different environments. Fixing them incorrectly may negatively impact optimization performance leading notably to insufficient or redundant learning. Insufficient learning (due to convergence to local optima) results in under-performing policies whilst redundant learning wastes time and resources. The effects are further exacerbated when using single policies to solve multi-task learning problems. Observing that the Evidence Lower Bound (ELBO) used in Variational Auto-Encoders correlates wit"},"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":"2010.08252","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-10-16T08:58:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bdd7f30f4fa0eccaaebffe04aa593b98e3c5fffbbb0d19684de407b03e0c5ac5","abstract_canon_sha256":"24c8f993a161946b2b5d653125b792dc634c2fc1a55dc1ca5d336aef780fe4d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:14.397067Z","signature_b64":"4tAjfbtYQp6qAV5bGqHJsGFSi3bspYo9fbjawpz0z5mIhh3Sk9EZl+xVPhPSiBMowLGYKnyZTmTJ31r9gO1NAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2442261fb3b0e32985ed4110a63d3c12d5c328b3a7a3c1a79eb5155910945c7e","last_reissued_at":"2026-07-05T02:26:14.396561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:14.396561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperparameter Auto-tuning in Self-Supervised Robotic Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Hongmin Wu, Jiancong Huang, Juan Rojas, Matthieu Zimmer, Paul Weng, Yisheng Guan","submitted_at":"2020-10-16T08:58:24Z","abstract_excerpt":"Policy optimization in reinforcement learning requires the selection of numerous hyperparameters across different environments. Fixing them incorrectly may negatively impact optimization performance leading notably to insufficient or redundant learning. Insufficient learning (due to convergence to local optima) results in under-performing policies whilst redundant learning wastes time and resources. The effects are further exacerbated when using single policies to solve multi-task learning problems. Observing that the Evidence Lower Bound (ELBO) used in Variational Auto-Encoders correlates wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08252","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/2010.08252/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":"2010.08252","created_at":"2026-07-05T02:26:14.396617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.08252v4","created_at":"2026-07-05T02:26:14.396617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08252","created_at":"2026-07-05T02:26:14.396617+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERBCMH5TWDRS","created_at":"2026-07-05T02:26:14.396617+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERBCMH5TWDRSTBPN","created_at":"2026-07-05T02:26:14.396617+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERBCMH5T","created_at":"2026-07-05T02:26:14.396617+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/ERBCMH5TWDRSTBPNIEIKMPJ4CL","json":"https://pith.science/pith/ERBCMH5TWDRSTBPNIEIKMPJ4CL.json","graph_json":"https://pith.science/api/pith-number/ERBCMH5TWDRSTBPNIEIKMPJ4CL/graph.json","events_json":"https://pith.science/api/pith-number/ERBCMH5TWDRSTBPNIEIKMPJ4CL/events.json","paper":"https://pith.science/paper/ERBCMH5T"},"agent_actions":{"view_html":"https://pith.science/pith/ERBCMH5TWDRSTBPNIEIKMPJ4CL","download_json":"https://pith.science/pith/ERBCMH5TWDRSTBPNIEIKMPJ4CL.json","view_paper":"https://pith.science/paper/ERBCMH5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.08252&json=true","fetch_graph":"https://pith.science/api/pith-number/ERBCMH5TWDRSTBPNIEIKMPJ4CL/graph.json","fetch_events":"https://pith.science/api/pith-number/ERBCMH5TWDRSTBPNIEIKMPJ4CL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERBCMH5TWDRSTBPNIEIKMPJ4CL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERBCMH5TWDRSTBPNIEIKMPJ4CL/action/storage_attestation","attest_author":"https://pith.science/pith/ERBCMH5TWDRSTBPNIEIKMPJ4CL/action/author_attestation","sign_citation":"https://pith.science/pith/ERBCMH5TWDRSTBPNIEIKMPJ4CL/action/citation_signature","submit_replication":"https://pith.science/pith/ERBCMH5TWDRSTBPNIEIKMPJ4CL/action/replication_record"}},"created_at":"2026-07-05T02:26:14.396617+00:00","updated_at":"2026-07-05T02:26:14.396617+00:00"}