{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:PHBRHQHSXBATHW2GLM7YTR5FEZ","short_pith_number":"pith:PHBRHQHS","schema_version":"1.0","canonical_sha256":"79c313c0f2b84133db465b3f89c7a5265a45b2fd946e94aa9f49e353dd71d1a7","source":{"kind":"arxiv","id":"1604.07704","version":1},"attestation_state":"computed","paper":{"title":"Tournament selection in zeroth-level classifier systems based on average reward reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Junying Wang, Zhao Li, Zhaoxiang Zang, Zhiping Dan","submitted_at":"2016-04-26T14:57:56Z","abstract_excerpt":"As a genetics-based machine learning technique, zeroth-level classifier system (ZCS) is based on a discounted reward reinforcement learning algorithm, bucket-brigade algorithm, which optimizes the discounted total reward received by an agent but is not suitable for all multi-step problems, especially large-size ones. There are some undiscounted reinforcement learning methods available, such as R-learning, which optimize the average reward per time step. In this paper, R-learning is used as the reinforcement learning employed by ZCS, to replace its discounted reward reinforcement learning appro"},"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":"1604.07704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-04-26T14:57:56Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c3439e97915620192c435d53fffdf2aa3690d0e472a09d3104571c589e61d756","abstract_canon_sha256":"8ec5ef6506d93714b855c04936e0f9129a7c65683248b0efffd366bbaead9f1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:12.259011Z","signature_b64":"JtzgqnN76nY/a2ixSE+X1Op4eQNRDgBBAlxkVyUSccoCXHAu1z0x7xefZJU3qcnUV+CSMSUqUy3W+3jPSVFCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79c313c0f2b84133db465b3f89c7a5265a45b2fd946e94aa9f49e353dd71d1a7","last_reissued_at":"2026-05-18T01:16:12.258350Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:12.258350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tournament selection in zeroth-level classifier systems based on average reward reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Junying Wang, Zhao Li, Zhaoxiang Zang, Zhiping Dan","submitted_at":"2016-04-26T14:57:56Z","abstract_excerpt":"As a genetics-based machine learning technique, zeroth-level classifier system (ZCS) is based on a discounted reward reinforcement learning algorithm, bucket-brigade algorithm, which optimizes the discounted total reward received by an agent but is not suitable for all multi-step problems, especially large-size ones. There are some undiscounted reinforcement learning methods available, such as R-learning, which optimize the average reward per time step. In this paper, R-learning is used as the reinforcement learning employed by ZCS, to replace its discounted reward reinforcement learning appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.07704","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":"1604.07704","created_at":"2026-05-18T01:16:12.258441+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.07704v1","created_at":"2026-05-18T01:16:12.258441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.07704","created_at":"2026-05-18T01:16:12.258441+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHBRHQHSXBAT","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHBRHQHSXBATHW2G","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHBRHQHS","created_at":"2026-05-18T12:30:39.010887+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/PHBRHQHSXBATHW2GLM7YTR5FEZ","json":"https://pith.science/pith/PHBRHQHSXBATHW2GLM7YTR5FEZ.json","graph_json":"https://pith.science/api/pith-number/PHBRHQHSXBATHW2GLM7YTR5FEZ/graph.json","events_json":"https://pith.science/api/pith-number/PHBRHQHSXBATHW2GLM7YTR5FEZ/events.json","paper":"https://pith.science/paper/PHBRHQHS"},"agent_actions":{"view_html":"https://pith.science/pith/PHBRHQHSXBATHW2GLM7YTR5FEZ","download_json":"https://pith.science/pith/PHBRHQHSXBATHW2GLM7YTR5FEZ.json","view_paper":"https://pith.science/paper/PHBRHQHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.07704&json=true","fetch_graph":"https://pith.science/api/pith-number/PHBRHQHSXBATHW2GLM7YTR5FEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PHBRHQHSXBATHW2GLM7YTR5FEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHBRHQHSXBATHW2GLM7YTR5FEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHBRHQHSXBATHW2GLM7YTR5FEZ/action/storage_attestation","attest_author":"https://pith.science/pith/PHBRHQHSXBATHW2GLM7YTR5FEZ/action/author_attestation","sign_citation":"https://pith.science/pith/PHBRHQHSXBATHW2GLM7YTR5FEZ/action/citation_signature","submit_replication":"https://pith.science/pith/PHBRHQHSXBATHW2GLM7YTR5FEZ/action/replication_record"}},"created_at":"2026-05-18T01:16:12.258441+00:00","updated_at":"2026-05-18T01:16:12.258441+00:00"}