{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:QB77G3BA6LXMRUMT4KPBMACAIU","short_pith_number":"pith:QB77G3BA","schema_version":"1.0","canonical_sha256":"807ff36c20f2eec8d193e29e1600404512036aa09e973e4c8dda7b15e6b6b649","source":{"kind":"arxiv","id":"1605.07496","version":3},"attestation_state":"computed","paper":{"title":"Alternating Optimisation and Quadrature for Robust Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jean-Baptiste Mouret, Kamil Ciosek, Konstantinos Chatzilygeroudis, Michael A. Osborne, Shimon Whiteson, Supratik Paul","submitted_at":"2016-05-24T15:15:57Z","abstract_excerpt":"Bayesian optimisation has been successfully applied to a variety of reinforcement learning problems. However, the traditional approach for learning optimal policies in simulators does not utilise the opportunity to improve learning by adjusting certain environment variables: state features that are unobservable and randomly determined by the environment in a physical setting but are controllable in a simulator. This paper considers the problem of finding a robust policy while taking into account the impact of environment variables. We present Alternating Optimisation and Quadrature (ALOQ), whi"},"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":"1605.07496","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-24T15:15:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"63339bf49d426b0335c6c0d173603c9aa877cd1778929e208f63b4f300b58859","abstract_canon_sha256":"b6c07c60be9ba25080535c32899403235a8477d86d80f8f8a9b9bdfbda3c39cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:53.283714Z","signature_b64":"wlXvvjLVF5hSwgHmAfBeBAklJ3n+kqwSxIy61uIocc2V6uMnfniEOodCcIPwg0Wh2+SMfL0+6deffLtHDhzPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"807ff36c20f2eec8d193e29e1600404512036aa09e973e4c8dda7b15e6b6b649","last_reissued_at":"2026-05-18T00:27:53.283213Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:53.283213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alternating Optimisation and Quadrature for Robust Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jean-Baptiste Mouret, Kamil Ciosek, Konstantinos Chatzilygeroudis, Michael A. Osborne, Shimon Whiteson, Supratik Paul","submitted_at":"2016-05-24T15:15:57Z","abstract_excerpt":"Bayesian optimisation has been successfully applied to a variety of reinforcement learning problems. However, the traditional approach for learning optimal policies in simulators does not utilise the opportunity to improve learning by adjusting certain environment variables: state features that are unobservable and randomly determined by the environment in a physical setting but are controllable in a simulator. This paper considers the problem of finding a robust policy while taking into account the impact of environment variables. We present Alternating Optimisation and Quadrature (ALOQ), whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07496","kind":"arxiv","version":3},"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":"1605.07496","created_at":"2026-05-18T00:27:53.283293+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.07496v3","created_at":"2026-05-18T00:27:53.283293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07496","created_at":"2026-05-18T00:27:53.283293+00:00"},{"alias_kind":"pith_short_12","alias_value":"QB77G3BA6LXM","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"QB77G3BA6LXMRUMT","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"QB77G3BA","created_at":"2026-05-18T12:30:39.010887+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/QB77G3BA6LXMRUMT4KPBMACAIU","json":"https://pith.science/pith/QB77G3BA6LXMRUMT4KPBMACAIU.json","graph_json":"https://pith.science/api/pith-number/QB77G3BA6LXMRUMT4KPBMACAIU/graph.json","events_json":"https://pith.science/api/pith-number/QB77G3BA6LXMRUMT4KPBMACAIU/events.json","paper":"https://pith.science/paper/QB77G3BA"},"agent_actions":{"view_html":"https://pith.science/pith/QB77G3BA6LXMRUMT4KPBMACAIU","download_json":"https://pith.science/pith/QB77G3BA6LXMRUMT4KPBMACAIU.json","view_paper":"https://pith.science/paper/QB77G3BA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.07496&json=true","fetch_graph":"https://pith.science/api/pith-number/QB77G3BA6LXMRUMT4KPBMACAIU/graph.json","fetch_events":"https://pith.science/api/pith-number/QB77G3BA6LXMRUMT4KPBMACAIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QB77G3BA6LXMRUMT4KPBMACAIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QB77G3BA6LXMRUMT4KPBMACAIU/action/storage_attestation","attest_author":"https://pith.science/pith/QB77G3BA6LXMRUMT4KPBMACAIU/action/author_attestation","sign_citation":"https://pith.science/pith/QB77G3BA6LXMRUMT4KPBMACAIU/action/citation_signature","submit_replication":"https://pith.science/pith/QB77G3BA6LXMRUMT4KPBMACAIU/action/replication_record"}},"created_at":"2026-05-18T00:27:53.283293+00:00","updated_at":"2026-05-18T00:27:53.283293+00:00"}