{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6WZSZUQMRLGSYERQNKLFW3D3ZQ","short_pith_number":"pith:6WZSZUQM","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"},"canonical_sha256":"f5b32cd20c8acd2c12306a965b6c7bcc3f70fffff0f61ebb43ebb8b7ecfdee4d","source":{"kind":"arxiv","id":"1805.11706","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11706","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11706v4","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11706","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"pith_short_12","alias_value":"6WZSZUQMRLGS","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6WZSZUQMRLGSYERQ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6WZSZUQM","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6WZSZUQMRLGSYERQNKLFW3D3ZQ","target":"record","payload":{"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"},"canonical_sha256":"f5b32cd20c8acd2c12306a965b6c7bcc3f70fffff0f61ebb43ebb8b7ecfdee4d","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"},"source_kind":"arxiv","source_id":"1805.11706","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DBvamkS83f50JE+i55hRBqUJzUbrN7O+iYTkaIKcxWoxdjpVLHLv6dHod7XCxV+5XA3HYEwsKxUJ8QOLZ5vgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:58:42.010006Z"},"content_sha256":"78216ac79c52d40b32e65655e964f93542d9036d266ee79b29c63e8529824ae9","schema_version":"1.0","event_id":"sha256:78216ac79c52d40b32e65655e964f93542d9036d266ee79b29c63e8529824ae9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6WZSZUQMRLGSYERQNKLFW3D3ZQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z4vKSSzvWkMc3rH7ANTDBHa7xTtaB3+lNMJdFQAH0a2aU/5rD0BCkpsnMhFADCPhr/+NaaINbC1BMeicjt2VDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:58:42.010407Z"},"content_sha256":"fed243d7d06155dd9bfd846aae053d2ec6fb0aaaf8ae5ddd18076afc02283301","schema_version":"1.0","event_id":"sha256:fed243d7d06155dd9bfd846aae053d2ec6fb0aaaf8ae5ddd18076afc02283301"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ/bundle.json","state_url":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-29T16:58:42Z","links":{"resolver":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ","bundle":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ/bundle.json","state":"https://pith.science/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6WZSZUQMRLGSYERQNKLFW3D3ZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6WZSZUQMRLGSYERQNKLFW3D3ZQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1b69f3d1fb87d133659bae5e36d424016c7fef9ffdb0bfde8f46df88314bb87b","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T20:57:19Z","title_canon_sha256":"8e33706f7a2df96e81fd8854acf620162af42edffaa774ec37aae96daf58f148"},"schema_version":"1.0","source":{"id":"1805.11706","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11706","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11706v4","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11706","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"pith_short_12","alias_value":"6WZSZUQMRLGS","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6WZSZUQMRLGSYERQ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6WZSZUQM","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:fed243d7d06155dd9bfd846aae053d2ec6fb0aaaf8ae5ddd18076afc02283301","target":"graph","created_at":"2026-05-17T23:57:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Keith W. Ross, Quan Vuong, Yiming Zhang","cross_cats":["cs.AI","cs.RO","cs.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T20:57:19Z","title":"Supervised Policy Update for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11706","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:78216ac79c52d40b32e65655e964f93542d9036d266ee79b29c63e8529824ae9","target":"record","created_at":"2026-05-17T23:57:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1b69f3d1fb87d133659bae5e36d424016c7fef9ffdb0bfde8f46df88314bb87b","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T20:57:19Z","title_canon_sha256":"8e33706f7a2df96e81fd8854acf620162af42edffaa774ec37aae96daf58f148"},"schema_version":"1.0","source":{"id":"1805.11706","kind":"arxiv","version":4}},"canonical_sha256":"f5b32cd20c8acd2c12306a965b6c7bcc3f70fffff0f61ebb43ebb8b7ecfdee4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5b32cd20c8acd2c12306a965b6c7bcc3f70fffff0f61ebb43ebb8b7ecfdee4d","first_computed_at":"2026-05-17T23:57:31.884325Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:31.884325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RRc0/PK+Zp1YG2tEYwQN81dvjlaeCnYB4Bnp39nLmckMh/5fpd/ySWmDwrxwwc2ExyeWfz+oCGU/nloVEaCADw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:31.884751Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.11706","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78216ac79c52d40b32e65655e964f93542d9036d266ee79b29c63e8529824ae9","sha256:fed243d7d06155dd9bfd846aae053d2ec6fb0aaaf8ae5ddd18076afc02283301"],"state_sha256":"08882d0fc363a7f4d8803ccac4556cf71df068f43a6500fca6509bf75c5cf6d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/aiZIcVAHxcdcLbOZHUY5P+EifiljoQWMpQGCBt3cNOSRYQh0A4cLrywO/yH1lYfCud9Lz62g9Q3UJUKNcJcDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T16:58:42.012900Z","bundle_sha256":"be46776b089a93878b13a320909dfa7c481bfee8c1d0a83b6b6edcd251619b15"}}