{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AK2E7PFPDFNUIHCBIOHPHSALQU","short_pith_number":"pith:AK2E7PFP","schema_version":"1.0","canonical_sha256":"02b44fbcaf195b441c41438ef3c80b853172ead2b8101495198b1e02f3cf413f","source":{"kind":"arxiv","id":"1901.00949","version":1},"attestation_state":"computed","paper":{"title":"Machine Teaching in Hierarchical Genetic Reinforcement Learning: Curriculum Design of Reward Functions for Swarm Shepherding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hussein Abbass, Nicholas R. Clayton","submitted_at":"2019-01-04T00:10:46Z","abstract_excerpt":"The design of reward functions in reinforcement learning is a human skill that comes with experience. Unfortunately, there is not any methodology in the literature that could guide a human to design the reward function or to allow a human to transfer the skills developed in designing reward functions to another human and in a systematic manner. In this paper, we use Systematic Instructional Design, an approach in human education, to engineer a machine education methodology to design reward functions for reinforcement learning. We demonstrate the methodology in designing a hierarchical genetic "},"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":"1901.00949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-01-04T00:10:46Z","cross_cats_sorted":[],"title_canon_sha256":"a9d848da7f36f3575ece93d912836c4ed639be9ca81c67b3b70b88f58c1c5ccd","abstract_canon_sha256":"5df4ebbbeb7aa7a1a2e37ec260d0374563fc3ec4ec312a2a7e300169a08e2f67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:57.605266Z","signature_b64":"4MQrQ8U02lTgNCVvGCNdIPC+WOYianun9czdhAYWKwQL9wS3KBX6yQfG7Xih5K4hAS+bIHUZoX2denDT8yYdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02b44fbcaf195b441c41438ef3c80b853172ead2b8101495198b1e02f3cf413f","last_reissued_at":"2026-05-17T23:56:57.604701Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:57.604701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Teaching in Hierarchical Genetic Reinforcement Learning: Curriculum Design of Reward Functions for Swarm Shepherding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hussein Abbass, Nicholas R. Clayton","submitted_at":"2019-01-04T00:10:46Z","abstract_excerpt":"The design of reward functions in reinforcement learning is a human skill that comes with experience. Unfortunately, there is not any methodology in the literature that could guide a human to design the reward function or to allow a human to transfer the skills developed in designing reward functions to another human and in a systematic manner. In this paper, we use Systematic Instructional Design, an approach in human education, to engineer a machine education methodology to design reward functions for reinforcement learning. We demonstrate the methodology in designing a hierarchical genetic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.00949","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":"1901.00949","created_at":"2026-05-17T23:56:57.604784+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.00949v1","created_at":"2026-05-17T23:56:57.604784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00949","created_at":"2026-05-17T23:56:57.604784+00:00"},{"alias_kind":"pith_short_12","alias_value":"AK2E7PFPDFNU","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"AK2E7PFPDFNUIHCB","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"AK2E7PFP","created_at":"2026-05-18T12:33:12.712433+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/AK2E7PFPDFNUIHCBIOHPHSALQU","json":"https://pith.science/pith/AK2E7PFPDFNUIHCBIOHPHSALQU.json","graph_json":"https://pith.science/api/pith-number/AK2E7PFPDFNUIHCBIOHPHSALQU/graph.json","events_json":"https://pith.science/api/pith-number/AK2E7PFPDFNUIHCBIOHPHSALQU/events.json","paper":"https://pith.science/paper/AK2E7PFP"},"agent_actions":{"view_html":"https://pith.science/pith/AK2E7PFPDFNUIHCBIOHPHSALQU","download_json":"https://pith.science/pith/AK2E7PFPDFNUIHCBIOHPHSALQU.json","view_paper":"https://pith.science/paper/AK2E7PFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.00949&json=true","fetch_graph":"https://pith.science/api/pith-number/AK2E7PFPDFNUIHCBIOHPHSALQU/graph.json","fetch_events":"https://pith.science/api/pith-number/AK2E7PFPDFNUIHCBIOHPHSALQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AK2E7PFPDFNUIHCBIOHPHSALQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AK2E7PFPDFNUIHCBIOHPHSALQU/action/storage_attestation","attest_author":"https://pith.science/pith/AK2E7PFPDFNUIHCBIOHPHSALQU/action/author_attestation","sign_citation":"https://pith.science/pith/AK2E7PFPDFNUIHCBIOHPHSALQU/action/citation_signature","submit_replication":"https://pith.science/pith/AK2E7PFPDFNUIHCBIOHPHSALQU/action/replication_record"}},"created_at":"2026-05-17T23:56:57.604784+00:00","updated_at":"2026-05-17T23:56:57.604784+00:00"}