{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZMIPH4TJAMQS2X5BSKLTLBS6B5","short_pith_number":"pith:ZMIPH4TJ","schema_version":"1.0","canonical_sha256":"cb10f3f26903212d5fa1929735865e0f5fd255a83d513465f081cdbe2ce9a14f","source":{"kind":"arxiv","id":"1709.06917","version":2},"attestation_state":"computed","paper":{"title":"Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.RO","authors_text":"Jean-Baptiste Mouret, Konstantinos Chatzilygeroudis","submitted_at":"2017-09-20T15:03:47Z","abstract_excerpt":"The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. Among the few proposed approaches, the recently introduced Black-DROPS algorithm exploits a black-box optimization algorithm to achieve both high data-efficiency and good computation times when several cores are used; nevertheless, like all model-based policy search approaches, Black-DROPS does not scale to high dimensional"},"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":"1709.06917","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-20T15:03:47Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"ff52ba3a7274684804499b5519cbbb9c3674f916da7f77ee83455c47d71ea595","abstract_canon_sha256":"d5a6153a177f99ae6b127ddb7f61b59dbf6acab2498889afefc6998762ffba5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:25.189730Z","signature_b64":"cAL9mg5GRwmFAXD81/t5gchltkKDTAYX3QfZP8Q6YrikMA2W69BwD4oVYDLpC+udnfBuuZD3KMp0QPd4J3KeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb10f3f26903212d5fa1929735865e0f5fd255a83d513465f081cdbe2ce9a14f","last_reissued_at":"2026-05-18T00:21:25.189006Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:25.189006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.RO","authors_text":"Jean-Baptiste Mouret, Konstantinos Chatzilygeroudis","submitted_at":"2017-09-20T15:03:47Z","abstract_excerpt":"The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. Among the few proposed approaches, the recently introduced Black-DROPS algorithm exploits a black-box optimization algorithm to achieve both high data-efficiency and good computation times when several cores are used; nevertheless, like all model-based policy search approaches, Black-DROPS does not scale to high dimensional"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06917","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":""},"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":"1709.06917","created_at":"2026-05-18T00:21:25.189135+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.06917v2","created_at":"2026-05-18T00:21:25.189135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06917","created_at":"2026-05-18T00:21:25.189135+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZMIPH4TJAMQS","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZMIPH4TJAMQS2X5B","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZMIPH4TJ","created_at":"2026-05-18T12:31:59.375834+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/ZMIPH4TJAMQS2X5BSKLTLBS6B5","json":"https://pith.science/pith/ZMIPH4TJAMQS2X5BSKLTLBS6B5.json","graph_json":"https://pith.science/api/pith-number/ZMIPH4TJAMQS2X5BSKLTLBS6B5/graph.json","events_json":"https://pith.science/api/pith-number/ZMIPH4TJAMQS2X5BSKLTLBS6B5/events.json","paper":"https://pith.science/paper/ZMIPH4TJ"},"agent_actions":{"view_html":"https://pith.science/pith/ZMIPH4TJAMQS2X5BSKLTLBS6B5","download_json":"https://pith.science/pith/ZMIPH4TJAMQS2X5BSKLTLBS6B5.json","view_paper":"https://pith.science/paper/ZMIPH4TJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.06917&json=true","fetch_graph":"https://pith.science/api/pith-number/ZMIPH4TJAMQS2X5BSKLTLBS6B5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZMIPH4TJAMQS2X5BSKLTLBS6B5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZMIPH4TJAMQS2X5BSKLTLBS6B5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZMIPH4TJAMQS2X5BSKLTLBS6B5/action/storage_attestation","attest_author":"https://pith.science/pith/ZMIPH4TJAMQS2X5BSKLTLBS6B5/action/author_attestation","sign_citation":"https://pith.science/pith/ZMIPH4TJAMQS2X5BSKLTLBS6B5/action/citation_signature","submit_replication":"https://pith.science/pith/ZMIPH4TJAMQS2X5BSKLTLBS6B5/action/replication_record"}},"created_at":"2026-05-18T00:21:25.189135+00:00","updated_at":"2026-05-18T00:21:25.189135+00:00"}