{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LMB723PQ5OFZJ3EANHXYOUCJBO","short_pith_number":"pith:LMB723PQ","schema_version":"1.0","canonical_sha256":"5b03fd6df0eb8b94ec8069ef8750490bb08dbe43fb91c3dabb84259ee2a91ff2","source":{"kind":"arxiv","id":"1906.06178","version":1},"attestation_state":"computed","paper":{"title":"Curriculum Learning for Cumulative Return Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christiano Coletto Christakou, Francesco Foglino, Matteo Leonetti, Ricardo Luna Gutierrez","submitted_at":"2019-06-13T14:38:56Z","abstract_excerpt":"Curriculum learning has been successfully used in reinforcement learning to accelerate the learning process, through knowledge transfer between tasks of increasing complexity. Critical tasks, in which suboptimal exploratory actions must be minimized, can benefit from curriculum learning, and its ability to shape exploration through transfer. We propose a task sequencing algorithm maximizing the cumulative return, that is, the return obtained by the agent across all the learning episodes. By maximizing the cumulative return, the agent not only aims at achieving high rewards as fast as possible,"},"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":"1906.06178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T14:38:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f4fa110ddf384515edadc64f5ce466a3da9e45e326d6172619cef86c6589fd26","abstract_canon_sha256":"f1c875222558ffa54c1f589171cffc80f6fb3cde3acb39da91a1d0c486f8860b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:19.469382Z","signature_b64":"ti5o52LdazzNITIu4weycr90bALKZoSkqToFfYjVPTWUzKqwj6XDaL2enkMjmJYq3cp/uPJm5qcVRd5ez463Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b03fd6df0eb8b94ec8069ef8750490bb08dbe43fb91c3dabb84259ee2a91ff2","last_reissued_at":"2026-05-17T23:43:19.468908Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:19.468908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curriculum Learning for Cumulative Return Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christiano Coletto Christakou, Francesco Foglino, Matteo Leonetti, Ricardo Luna Gutierrez","submitted_at":"2019-06-13T14:38:56Z","abstract_excerpt":"Curriculum learning has been successfully used in reinforcement learning to accelerate the learning process, through knowledge transfer between tasks of increasing complexity. Critical tasks, in which suboptimal exploratory actions must be minimized, can benefit from curriculum learning, and its ability to shape exploration through transfer. We propose a task sequencing algorithm maximizing the cumulative return, that is, the return obtained by the agent across all the learning episodes. By maximizing the cumulative return, the agent not only aims at achieving high rewards as fast as possible,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06178","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":"1906.06178","created_at":"2026-05-17T23:43:19.468967+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.06178v1","created_at":"2026-05-17T23:43:19.468967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06178","created_at":"2026-05-17T23:43:19.468967+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMB723PQ5OFZ","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMB723PQ5OFZJ3EA","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMB723PQ","created_at":"2026-05-18T12:33:21.387695+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/LMB723PQ5OFZJ3EANHXYOUCJBO","json":"https://pith.science/pith/LMB723PQ5OFZJ3EANHXYOUCJBO.json","graph_json":"https://pith.science/api/pith-number/LMB723PQ5OFZJ3EANHXYOUCJBO/graph.json","events_json":"https://pith.science/api/pith-number/LMB723PQ5OFZJ3EANHXYOUCJBO/events.json","paper":"https://pith.science/paper/LMB723PQ"},"agent_actions":{"view_html":"https://pith.science/pith/LMB723PQ5OFZJ3EANHXYOUCJBO","download_json":"https://pith.science/pith/LMB723PQ5OFZJ3EANHXYOUCJBO.json","view_paper":"https://pith.science/paper/LMB723PQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.06178&json=true","fetch_graph":"https://pith.science/api/pith-number/LMB723PQ5OFZJ3EANHXYOUCJBO/graph.json","fetch_events":"https://pith.science/api/pith-number/LMB723PQ5OFZJ3EANHXYOUCJBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMB723PQ5OFZJ3EANHXYOUCJBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMB723PQ5OFZJ3EANHXYOUCJBO/action/storage_attestation","attest_author":"https://pith.science/pith/LMB723PQ5OFZJ3EANHXYOUCJBO/action/author_attestation","sign_citation":"https://pith.science/pith/LMB723PQ5OFZJ3EANHXYOUCJBO/action/citation_signature","submit_replication":"https://pith.science/pith/LMB723PQ5OFZJ3EANHXYOUCJBO/action/replication_record"}},"created_at":"2026-05-17T23:43:19.468967+00:00","updated_at":"2026-05-17T23:43:19.468967+00:00"}