{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LPEJSQPQWBK55VZH3ZW6XAEU3E","short_pith_number":"pith:LPEJSQPQ","schema_version":"1.0","canonical_sha256":"5bc89941f0b055ded727de6deb8094d92420e412233199097f04a5c7b4de85fd","source":{"kind":"arxiv","id":"1811.07745","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with A* and a Deep Heuristic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adham Ghazali, Ariel Keselman, Majed Jubeh, Sergey Ten","submitted_at":"2018-11-19T15:15:18Z","abstract_excerpt":"A* is a popular path-finding algorithm, but it can only be applied to those domains where a good heuristic function is known. Inspired by recent methods combining Deep Neural Networks (DNNs) and trees, this study demonstrates how to train a heuristic represented by a DNN and combine it with A*. This new algorithm which we call aleph-star can be used efficiently in domains where the input to the heuristic could be processed by a neural network. We compare aleph-star to N-Step Deep Q-Learning (DQN Mnih et al. 2013) in a driving simulation with pixel-based input, and demonstrate significantly bet"},"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":"1811.07745","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T15:15:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ccb9853a5008309257911272b849cf9b9d234823f1ad56c7147f1233ce9e0748","abstract_canon_sha256":"ec23e4bd05497a14d576798028a276a1055568c4d9c2d56a2b8abd62ec86099e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:23.557728Z","signature_b64":"O6VIAn4NtGSOkTqg85vETa84l2NDrWcSUG1PaMPcXREj5Le43+UTGs5ytQavR9RKNHW4KRsyVShnRh0WntwfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bc89941f0b055ded727de6deb8094d92420e412233199097f04a5c7b4de85fd","last_reissued_at":"2026-05-18T00:00:23.556767Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:23.556767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with A* and a Deep Heuristic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adham Ghazali, Ariel Keselman, Majed Jubeh, Sergey Ten","submitted_at":"2018-11-19T15:15:18Z","abstract_excerpt":"A* is a popular path-finding algorithm, but it can only be applied to those domains where a good heuristic function is known. Inspired by recent methods combining Deep Neural Networks (DNNs) and trees, this study demonstrates how to train a heuristic represented by a DNN and combine it with A*. This new algorithm which we call aleph-star can be used efficiently in domains where the input to the heuristic could be processed by a neural network. We compare aleph-star to N-Step Deep Q-Learning (DQN Mnih et al. 2013) in a driving simulation with pixel-based input, and demonstrate significantly bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07745","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":""},"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":"1811.07745","created_at":"2026-05-18T00:00:23.557089+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.07745v1","created_at":"2026-05-18T00:00:23.557089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07745","created_at":"2026-05-18T00:00:23.557089+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPEJSQPQWBK5","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPEJSQPQWBK55VZH","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPEJSQPQ","created_at":"2026-05-18T12:32:37.024351+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/LPEJSQPQWBK55VZH3ZW6XAEU3E","json":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E.json","graph_json":"https://pith.science/api/pith-number/LPEJSQPQWBK55VZH3ZW6XAEU3E/graph.json","events_json":"https://pith.science/api/pith-number/LPEJSQPQWBK55VZH3ZW6XAEU3E/events.json","paper":"https://pith.science/paper/LPEJSQPQ"},"agent_actions":{"view_html":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E","download_json":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E.json","view_paper":"https://pith.science/paper/LPEJSQPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.07745&json=true","fetch_graph":"https://pith.science/api/pith-number/LPEJSQPQWBK55VZH3ZW6XAEU3E/graph.json","fetch_events":"https://pith.science/api/pith-number/LPEJSQPQWBK55VZH3ZW6XAEU3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E/action/storage_attestation","attest_author":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E/action/author_attestation","sign_citation":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E/action/citation_signature","submit_replication":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E/action/replication_record"}},"created_at":"2026-05-18T00:00:23.557089+00:00","updated_at":"2026-05-18T00:00:23.557089+00:00"}