{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RJWHXFRC3OXXJCWIWV7UJOBIRS","short_pith_number":"pith:RJWHXFRC","schema_version":"1.0","canonical_sha256":"8a6c7b9622dbaf748ac8b57f44b8288cb32dd4de3941b6b0cfd5d85c2136ac35","source":{"kind":"arxiv","id":"2312.11768","version":1},"attestation_state":"computed","paper":{"title":"Curriculum Learning for Cooperation in Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Clod\\'eric Mars, Matthew E. Taylor, Rupali Bhati, Sai Krishna Gottipati","submitted_at":"2023-12-19T00:59:16Z","abstract_excerpt":"While there has been significant progress in curriculum learning and continuous learning for training agents to generalize across a wide variety of environments in the context of single-agent reinforcement learning, it is unclear if these algorithms would still be valid in a multi-agent setting. In a competitive setting, a learning agent can be trained by making it compete with a curriculum of increasingly skilled opponents. However, a general intelligent agent should also be able to learn to act around other agents and cooperate with them to achieve common goals. When cooperating with other a"},"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":"2312.11768","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-19T00:59:16Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"593ce6ab6eb7ffeec3b523b5d7d3087646ac97f18c51f311ca7cf98933084e9b","abstract_canon_sha256":"a186eaf1238620fdd467212e9c113489c129459efa054f4169b4ef11f5be3844"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:53.944224Z","signature_b64":"hwOFUfstYUcZ9gqGGqhr2sVXGrUByqAcPG1vby7+CpBTq2XcbVQZ/zvTB3nJLOeUluYNi4jCM1II1H7GuoQdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a6c7b9622dbaf748ac8b57f44b8288cb32dd4de3941b6b0cfd5d85c2136ac35","last_reissued_at":"2026-07-05T07:25:53.943875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:53.943875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curriculum Learning for Cooperation in Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Clod\\'eric Mars, Matthew E. Taylor, Rupali Bhati, Sai Krishna Gottipati","submitted_at":"2023-12-19T00:59:16Z","abstract_excerpt":"While there has been significant progress in curriculum learning and continuous learning for training agents to generalize across a wide variety of environments in the context of single-agent reinforcement learning, it is unclear if these algorithms would still be valid in a multi-agent setting. In a competitive setting, a learning agent can be trained by making it compete with a curriculum of increasingly skilled opponents. However, a general intelligent agent should also be able to learn to act around other agents and cooperate with them to achieve common goals. When cooperating with other a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11768","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.11768/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2312.11768","created_at":"2026-07-05T07:25:53.943933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11768v1","created_at":"2026-07-05T07:25:53.943933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11768","created_at":"2026-07-05T07:25:53.943933+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJWHXFRC3OXX","created_at":"2026-07-05T07:25:53.943933+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJWHXFRC3OXXJCWI","created_at":"2026-07-05T07:25:53.943933+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJWHXFRC","created_at":"2026-07-05T07:25:53.943933+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/RJWHXFRC3OXXJCWIWV7UJOBIRS","json":"https://pith.science/pith/RJWHXFRC3OXXJCWIWV7UJOBIRS.json","graph_json":"https://pith.science/api/pith-number/RJWHXFRC3OXXJCWIWV7UJOBIRS/graph.json","events_json":"https://pith.science/api/pith-number/RJWHXFRC3OXXJCWIWV7UJOBIRS/events.json","paper":"https://pith.science/paper/RJWHXFRC"},"agent_actions":{"view_html":"https://pith.science/pith/RJWHXFRC3OXXJCWIWV7UJOBIRS","download_json":"https://pith.science/pith/RJWHXFRC3OXXJCWIWV7UJOBIRS.json","view_paper":"https://pith.science/paper/RJWHXFRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11768&json=true","fetch_graph":"https://pith.science/api/pith-number/RJWHXFRC3OXXJCWIWV7UJOBIRS/graph.json","fetch_events":"https://pith.science/api/pith-number/RJWHXFRC3OXXJCWIWV7UJOBIRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJWHXFRC3OXXJCWIWV7UJOBIRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJWHXFRC3OXXJCWIWV7UJOBIRS/action/storage_attestation","attest_author":"https://pith.science/pith/RJWHXFRC3OXXJCWIWV7UJOBIRS/action/author_attestation","sign_citation":"https://pith.science/pith/RJWHXFRC3OXXJCWIWV7UJOBIRS/action/citation_signature","submit_replication":"https://pith.science/pith/RJWHXFRC3OXXJCWIWV7UJOBIRS/action/replication_record"}},"created_at":"2026-07-05T07:25:53.943933+00:00","updated_at":"2026-07-05T07:25:53.943933+00:00"}