{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FQ3U7ZVU2LFXPMGIYVOVJMIGD6","short_pith_number":"pith:FQ3U7ZVU","schema_version":"1.0","canonical_sha256":"2c374fe6b4d2cb77b0c8c55d54b1061fbbb5e71817d14b36e2bb7567b16ce699","source":{"kind":"arxiv","id":"1810.07254","version":1},"attestation_state":"computed","paper":{"title":"The Concept of Criticality in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amos Azaria, Yitzhak Spielberg","submitted_at":"2018-10-16T20:07:06Z","abstract_excerpt":"Reinforcement learning methods carry a well known bias-variance trade-off in n-step algorithms for optimal control. Unfortunately, this has rarely been addressed in current research. This trade-off principle holds independent of the choice of the algorithm, such as n-step SARSA, n-step Expected SARSA or n-step Tree backup. A small n results in a large bias, while a large n leads to large variance. The literature offers no straightforward recipe for the best choice of this value. While currently all n-step algorithms use a fixed value of n over the state space we extend the framework of n-step "},"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":"1810.07254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T20:07:06Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"10a7d0e112ffa4322b11c098d5ffbb960638f45ecf81de77e549de6ad1974f4f","abstract_canon_sha256":"ad47d931f27df4c634662e532c8d2bf5291d4b7b983144949bfe570490de454e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:59.035412Z","signature_b64":"+S+RkB7ERAylSzfsp+FTwc6Br95PVUubHjQkT7jozQPS+V5e8HndvydXSDuzCoHph45s0XqUzX9gNHVpRPwSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c374fe6b4d2cb77b0c8c55d54b1061fbbb5e71817d14b36e2bb7567b16ce699","last_reissued_at":"2026-05-18T00:02:59.034904Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:59.034904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Concept of Criticality in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amos Azaria, Yitzhak Spielberg","submitted_at":"2018-10-16T20:07:06Z","abstract_excerpt":"Reinforcement learning methods carry a well known bias-variance trade-off in n-step algorithms for optimal control. Unfortunately, this has rarely been addressed in current research. This trade-off principle holds independent of the choice of the algorithm, such as n-step SARSA, n-step Expected SARSA or n-step Tree backup. A small n results in a large bias, while a large n leads to large variance. The literature offers no straightforward recipe for the best choice of this value. While currently all n-step algorithms use a fixed value of n over the state space we extend the framework of n-step "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07254","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":"1810.07254","created_at":"2026-05-18T00:02:59.034980+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07254v1","created_at":"2026-05-18T00:02:59.034980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07254","created_at":"2026-05-18T00:02:59.034980+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQ3U7ZVU2LFX","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQ3U7ZVU2LFXPMGI","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQ3U7ZVU","created_at":"2026-05-18T12:32:25.280505+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/FQ3U7ZVU2LFXPMGIYVOVJMIGD6","json":"https://pith.science/pith/FQ3U7ZVU2LFXPMGIYVOVJMIGD6.json","graph_json":"https://pith.science/api/pith-number/FQ3U7ZVU2LFXPMGIYVOVJMIGD6/graph.json","events_json":"https://pith.science/api/pith-number/FQ3U7ZVU2LFXPMGIYVOVJMIGD6/events.json","paper":"https://pith.science/paper/FQ3U7ZVU"},"agent_actions":{"view_html":"https://pith.science/pith/FQ3U7ZVU2LFXPMGIYVOVJMIGD6","download_json":"https://pith.science/pith/FQ3U7ZVU2LFXPMGIYVOVJMIGD6.json","view_paper":"https://pith.science/paper/FQ3U7ZVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07254&json=true","fetch_graph":"https://pith.science/api/pith-number/FQ3U7ZVU2LFXPMGIYVOVJMIGD6/graph.json","fetch_events":"https://pith.science/api/pith-number/FQ3U7ZVU2LFXPMGIYVOVJMIGD6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQ3U7ZVU2LFXPMGIYVOVJMIGD6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQ3U7ZVU2LFXPMGIYVOVJMIGD6/action/storage_attestation","attest_author":"https://pith.science/pith/FQ3U7ZVU2LFXPMGIYVOVJMIGD6/action/author_attestation","sign_citation":"https://pith.science/pith/FQ3U7ZVU2LFXPMGIYVOVJMIGD6/action/citation_signature","submit_replication":"https://pith.science/pith/FQ3U7ZVU2LFXPMGIYVOVJMIGD6/action/replication_record"}},"created_at":"2026-05-18T00:02:59.034980+00:00","updated_at":"2026-05-18T00:02:59.034980+00:00"}