{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6WZSZUQMRLGSYERQNKLFW3D3ZQ","short_pith_number":"pith:6WZSZUQM","schema_version":"1.0","canonical_sha256":"f5b32cd20c8acd2c12306a965b6c7bcc3f70fffff0f61ebb43ebb8b7ecfdee4d","source":{"kind":"arxiv","id":"1805.11706","version":4},"attestation_state":"computed","paper":{"title":"Supervised Policy Update for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Keith W. Ross, Quan Vuong, Yiming Zhang","submitted_at":"2018-05-29T20:57:19Z","abstract_excerpt":"We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the non-parameterized proximal policy space. Using supervised regression, it then converts the optimal non-parameterized policy to a parameterized policy, from which it draws new samples. The methodology is general in that it applies to both discrete and continuous action spaces, and can handle a wide variety of proximity constraints for the non-parameterized opt"},"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":"1805.11706","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T20:57:19Z","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","stat.ML"],"title_canon_sha256":"8e33706f7a2df96e81fd8854acf620162af42edffaa774ec37aae96daf58f148","abstract_canon_sha256":"1b69f3d1fb87d133659bae5e36d424016c7fef9ffdb0bfde8f46df88314bb87b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:31.884751Z","signature_b64":"RRc0/PK+Zp1YG2tEYwQN81dvjlaeCnYB4Bnp39nLmckMh/5fpd/ySWmDwrxwwc2ExyeWfz+oCGU/nloVEaCADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5b32cd20c8acd2c12306a965b6c7bcc3f70fffff0f61ebb43ebb8b7ecfdee4d","last_reissued_at":"2026-05-17T23:57:31.884325Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:31.884325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Supervised Policy Update for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Keith W. Ross, Quan Vuong, Yiming Zhang","submitted_at":"2018-05-29T20:57:19Z","abstract_excerpt":"We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the non-parameterized proximal policy space. Using supervised regression, it then converts the optimal non-parameterized policy to a parameterized policy, from which it draws new samples. The methodology is general in that it applies to both discrete and continuous action spaces, and can handle a wide variety of proximity constraints for the non-parameterized opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11706","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":""},"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":"1805.11706","created_at":"2026-05-17T23:57:31.884390+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11706v4","created_at":"2026-05-17T23:57:31.884390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11706","created_at":"2026-05-17T23:57:31.884390+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WZSZUQMRLGS","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WZSZUQMRLGSYERQ","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WZSZUQM","created_at":"2026-05-18T12:32:11.075285+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/6WZSZUQMRLGSYERQNKLFW3D3ZQ","json":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ.json","graph_json":"https://pith.science/api/pith-number/6WZSZUQMRLGSYERQNKLFW3D3ZQ/graph.json","events_json":"https://pith.science/api/pith-number/6WZSZUQMRLGSYERQNKLFW3D3ZQ/events.json","paper":"https://pith.science/paper/6WZSZUQM"},"agent_actions":{"view_html":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ","download_json":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ.json","view_paper":"https://pith.science/paper/6WZSZUQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11706&json=true","fetch_graph":"https://pith.science/api/pith-number/6WZSZUQMRLGSYERQNKLFW3D3ZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6WZSZUQMRLGSYERQNKLFW3D3ZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ/action/storage_attestation","attest_author":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ/action/author_attestation","sign_citation":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ/action/citation_signature","submit_replication":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ/action/replication_record"}},"created_at":"2026-05-17T23:57:31.884390+00:00","updated_at":"2026-05-17T23:57:31.884390+00:00"}