{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4ARQQ6AQYLXOYL3CDHULDKW4PM","short_pith_number":"pith:4ARQQ6AQ","schema_version":"1.0","canonical_sha256":"e023087810c2eeec2f6219e8b1aadc7b3a0d4af006e75069d486dd917adb3ce3","source":{"kind":"arxiv","id":"2507.18867","version":1},"attestation_state":"computed","paper":{"title":"Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Chunlin Chen, Xiao Yin, Xuefei Wu, Yuanyang Zhu","submitted_at":"2025-07-25T00:59:10Z","abstract_excerpt":"Efficient exploration in multi-agent reinforcement learning (MARL) is a challenging problem when receiving only a team reward, especially in environments with sparse rewards. A powerful method to mitigate this issue involves crafting dense individual rewards to guide the agents toward efficient exploration. However, individual rewards generally rely on manually engineered shaping-reward functions that lack high-order intelligence, thus it behaves ineffectively than humans regarding learning and generalization in complex problems. To tackle these issues, we combine the above two paradigms and p"},"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":"2507.18867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T00:59:10Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"1e137f7c0ca371ece423e979a53305eea883cb24eec58aa4ecb57d59b591dfa0","abstract_canon_sha256":"2b90c7a6e1772838f25ad9778b5045567d87b2374e67570ad81b786534aa42ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:59.882063Z","signature_b64":"Y8Zh3cu/o5uWCw/TJ7uaN5r3ReajpDWlRDK9Ghp+o0f2HQBDrVU8aJfN0N1cAYLkg+NPQwcSL43uHKVCnxR1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e023087810c2eeec2f6219e8b1aadc7b3a0d4af006e75069d486dd917adb3ce3","last_reissued_at":"2026-07-05T11:42:59.881593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:59.881593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Chunlin Chen, Xiao Yin, Xuefei Wu, Yuanyang Zhu","submitted_at":"2025-07-25T00:59:10Z","abstract_excerpt":"Efficient exploration in multi-agent reinforcement learning (MARL) is a challenging problem when receiving only a team reward, especially in environments with sparse rewards. A powerful method to mitigate this issue involves crafting dense individual rewards to guide the agents toward efficient exploration. However, individual rewards generally rely on manually engineered shaping-reward functions that lack high-order intelligence, thus it behaves ineffectively than humans regarding learning and generalization in complex problems. To tackle these issues, we combine the above two paradigms and p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18867","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/2507.18867/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":"2507.18867","created_at":"2026-07-05T11:42:59.881651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18867v1","created_at":"2026-07-05T11:42:59.881651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18867","created_at":"2026-07-05T11:42:59.881651+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ARQQ6AQYLXO","created_at":"2026-07-05T11:42:59.881651+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ARQQ6AQYLXOYL3C","created_at":"2026-07-05T11:42:59.881651+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ARQQ6AQ","created_at":"2026-07-05T11:42:59.881651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM","json":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM.json","graph_json":"https://pith.science/api/pith-number/4ARQQ6AQYLXOYL3CDHULDKW4PM/graph.json","events_json":"https://pith.science/api/pith-number/4ARQQ6AQYLXOYL3CDHULDKW4PM/events.json","paper":"https://pith.science/paper/4ARQQ6AQ"},"agent_actions":{"view_html":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM","download_json":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM.json","view_paper":"https://pith.science/paper/4ARQQ6AQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18867&json=true","fetch_graph":"https://pith.science/api/pith-number/4ARQQ6AQYLXOYL3CDHULDKW4PM/graph.json","fetch_events":"https://pith.science/api/pith-number/4ARQQ6AQYLXOYL3CDHULDKW4PM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM/action/storage_attestation","attest_author":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM/action/author_attestation","sign_citation":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM/action/citation_signature","submit_replication":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM/action/replication_record"}},"created_at":"2026-07-05T11:42:59.881651+00:00","updated_at":"2026-07-05T11:42:59.881651+00:00"}