{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GVJ45LT6SYBH3CHU6AYQFLYVDW","short_pith_number":"pith:GVJ45LT6","canonical_record":{"source":{"id":"1910.02426","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-06T11:51:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"642dcd41d20a877a9dc043d2738d9522246285804deaa23bdbf777f71bb12fa4","abstract_canon_sha256":"c264d9f819303bdedf47d0f6f086c2c7c28d2bebb7e936ea5c545e9f62fc9f9d"},"schema_version":"1.0"},"canonical_sha256":"3553ceae7e96027d88f4f03102af151d8559868d6092bc27cd460c7fe2d4270f","source":{"kind":"arxiv","id":"1910.02426","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.02426","created_at":"2026-07-05T00:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"1910.02426v1","created_at":"2026-07-05T00:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02426","created_at":"2026-07-05T00:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"GVJ45LT6SYBH","created_at":"2026-07-05T00:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"GVJ45LT6SYBH3CHU","created_at":"2026-07-05T00:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"GVJ45LT6","created_at":"2026-07-05T00:10:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GVJ45LT6SYBH3CHU6AYQFLYVDW","target":"record","payload":{"canonical_record":{"source":{"id":"1910.02426","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-06T11:51:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"642dcd41d20a877a9dc043d2738d9522246285804deaa23bdbf777f71bb12fa4","abstract_canon_sha256":"c264d9f819303bdedf47d0f6f086c2c7c28d2bebb7e936ea5c545e9f62fc9f9d"},"schema_version":"1.0"},"canonical_sha256":"3553ceae7e96027d88f4f03102af151d8559868d6092bc27cd460c7fe2d4270f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:08.260064Z","signature_b64":"4P2xGjDdNmWjJuC8oFX0inN2wdGNnroV5kk9RaiplAS8VW/sFSr6Xe6MIRUYTiSEMyLtXr+au79p/wasPFvKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3553ceae7e96027d88f4f03102af151d8559868d6092bc27cd460c7fe2d4270f","last_reissued_at":"2026-07-05T00:10:08.259721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:08.259721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.02426","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:10:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/UG8xXRC7T660KSGiNF57B7r1hgC3ZpBVpu7q8FPy1HMLjrDa3/QdO4P1tE1DF/2BAswfARgdtxrEL8tr6VPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:42:22.372147Z"},"content_sha256":"88564dd23f770847cebbb0495899b4e40a14440468ff33fefd94277f5191de1e","schema_version":"1.0","event_id":"sha256:88564dd23f770847cebbb0495899b4e40a14440468ff33fefd94277f5191de1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GVJ45LT6SYBH3CHU6AYQFLYVDW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Biased Aggregation, Rollout, and Enhanced Policy Improvement for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dimitri Bertsekas","submitted_at":"2019-10-06T11:51:00Z","abstract_excerpt":"We propose a new aggregation framework for approximate dynamic programming, which provides a connection with rollout algorithms, approximate policy iteration, and other single and multistep lookahead methods. The central novel characteristic is the use of a bias function $V$ of the state, which biases the values of the aggregate cost function towards their correct levels. The classical aggregation framework is obtained when $V\\equiv0$, but our scheme works best when $V$ is a known reasonably good approximation to the optimal cost function $J^*$.\n  When $V$ is equal to the cost function $J_{\\mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02426","kind":"arxiv","version":1},"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/1910.02426/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:10:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3oHC61sGvFwGsS4dsKsPcqD9QRyrtCCWM2IpjU8KZZgfKN3asHYVo72KC57maTTBrIvZYUnxDiOwT0XL/aHuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:42:22.372644Z"},"content_sha256":"7ce24bf7ebd02a53b2ddea3e01351f798d76e921d55a88a5afb0de8a5629bfc1","schema_version":"1.0","event_id":"sha256:7ce24bf7ebd02a53b2ddea3e01351f798d76e921d55a88a5afb0de8a5629bfc1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GVJ45LT6SYBH3CHU6AYQFLYVDW/bundle.json","state_url":"https://pith.science/pith/GVJ45LT6SYBH3CHU6AYQFLYVDW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GVJ45LT6SYBH3CHU6AYQFLYVDW/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":"2026-08-05T07:42:22Z","links":{"resolver":"https://pith.science/pith/GVJ45LT6SYBH3CHU6AYQFLYVDW","bundle":"https://pith.science/pith/GVJ45LT6SYBH3CHU6AYQFLYVDW/bundle.json","state":"https://pith.science/pith/GVJ45LT6SYBH3CHU6AYQFLYVDW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GVJ45LT6SYBH3CHU6AYQFLYVDW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GVJ45LT6SYBH3CHU6AYQFLYVDW","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":"c264d9f819303bdedf47d0f6f086c2c7c28d2bebb7e936ea5c545e9f62fc9f9d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-06T11:51:00Z","title_canon_sha256":"642dcd41d20a877a9dc043d2738d9522246285804deaa23bdbf777f71bb12fa4"},"schema_version":"1.0","source":{"id":"1910.02426","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.02426","created_at":"2026-07-05T00:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"1910.02426v1","created_at":"2026-07-05T00:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02426","created_at":"2026-07-05T00:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"GVJ45LT6SYBH","created_at":"2026-07-05T00:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"GVJ45LT6SYBH3CHU","created_at":"2026-07-05T00:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"GVJ45LT6","created_at":"2026-07-05T00:10:08Z"}],"graph_snapshots":[{"event_id":"sha256:7ce24bf7ebd02a53b2ddea3e01351f798d76e921d55a88a5afb0de8a5629bfc1","target":"graph","created_at":"2026-07-05T00:10:08Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1910.02426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new aggregation framework for approximate dynamic programming, which provides a connection with rollout algorithms, approximate policy iteration, and other single and multistep lookahead methods. The central novel characteristic is the use of a bias function $V$ of the state, which biases the values of the aggregate cost function towards their correct levels. The classical aggregation framework is obtained when $V\\equiv0$, but our scheme works best when $V$ is a known reasonably good approximation to the optimal cost function $J^*$.\n  When $V$ is equal to the cost function $J_{\\mu","authors_text":"Dimitri Bertsekas","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-06T11:51:00Z","title":"Biased Aggregation, Rollout, and Enhanced Policy Improvement for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02426","kind":"arxiv","version":1},"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":"sha256:88564dd23f770847cebbb0495899b4e40a14440468ff33fefd94277f5191de1e","target":"record","created_at":"2026-07-05T00:10:08Z","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":"c264d9f819303bdedf47d0f6f086c2c7c28d2bebb7e936ea5c545e9f62fc9f9d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-06T11:51:00Z","title_canon_sha256":"642dcd41d20a877a9dc043d2738d9522246285804deaa23bdbf777f71bb12fa4"},"schema_version":"1.0","source":{"id":"1910.02426","kind":"arxiv","version":1}},"canonical_sha256":"3553ceae7e96027d88f4f03102af151d8559868d6092bc27cd460c7fe2d4270f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3553ceae7e96027d88f4f03102af151d8559868d6092bc27cd460c7fe2d4270f","first_computed_at":"2026-07-05T00:10:08.259721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:10:08.259721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4P2xGjDdNmWjJuC8oFX0inN2wdGNnroV5kk9RaiplAS8VW/sFSr6Xe6MIRUYTiSEMyLtXr+au79p/wasPFvKAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:10:08.260064Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.02426","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88564dd23f770847cebbb0495899b4e40a14440468ff33fefd94277f5191de1e","sha256:7ce24bf7ebd02a53b2ddea3e01351f798d76e921d55a88a5afb0de8a5629bfc1"],"state_sha256":"0f4fbcc3aa587a8864bb219e81a7eb93c6acfa46cff1ad772df71d2daa11f2e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"46oA/Y7JYZ2GmaAaADl8ZJsuInHAsm+3GxnY5dpHrMAikZMNulMItr8m+7UFnQAfti26DcxFW0pJGzaoXAlzCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:42:22.376062Z","bundle_sha256":"0cb6179f951089cb202c044cbcd26bab6dafb9fd5e258af2b2499507c2c1d37f"}}