{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EVITA3C5B6MUQKHUNMRNQQ7HXT","short_pith_number":"pith:EVITA3C5","schema_version":"1.0","canonical_sha256":"2551306c5d0f994828f46b22d843e7bccb1e7fd9320a72178d761f7e88883598","source":{"kind":"arxiv","id":"2002.02202","version":1},"attestation_state":"computed","paper":{"title":"Transfer Heterogeneous Knowledge Among Peer-to-Peer Teammates: A Model Distillation Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chao Wu, Kaigui Bian, Pan Zhou, Shuang Luo, Wei Du, Zeyue Xue","submitted_at":"2020-02-06T11:31:04Z","abstract_excerpt":"Peer-to-peer knowledge transfer in distributed environments has emerged as a promising method since it could accelerate learning and improve team-wide performance without relying on pre-trained teachers in deep reinforcement learning. However, for traditional peer-to-peer methods such as action advising, they have encountered difficulties in how to efficiently expressed knowledge and advice. As a result, we propose a brand new solution to reuse experiences and transfer value functions among multiple students via model distillation. But it is still challenging to transfer Q-function directly si"},"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":"2002.02202","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-02-06T11:31:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9c443ce041ee0a4c5dec019a265798b0d223ddb8cd320e0570f41e53cde95a06","abstract_canon_sha256":"4d1ed2fcafdbc701eb9c03c846c335a9f9b74b75a53233456c8454c49fbcb1f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:38:50.216618Z","signature_b64":"lrf9anVh0f5vLpDO5qsqtWeQBxhCf9JLOULPWiHlT7vIMZZ8YOxUdPDrNaZ1e4U7d3acABE3EhYj2Tnu57Y/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2551306c5d0f994828f46b22d843e7bccb1e7fd9320a72178d761f7e88883598","last_reissued_at":"2026-07-05T00:38:50.216211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:38:50.216211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transfer Heterogeneous Knowledge Among Peer-to-Peer Teammates: A Model Distillation Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chao Wu, Kaigui Bian, Pan Zhou, Shuang Luo, Wei Du, Zeyue Xue","submitted_at":"2020-02-06T11:31:04Z","abstract_excerpt":"Peer-to-peer knowledge transfer in distributed environments has emerged as a promising method since it could accelerate learning and improve team-wide performance without relying on pre-trained teachers in deep reinforcement learning. However, for traditional peer-to-peer methods such as action advising, they have encountered difficulties in how to efficiently expressed knowledge and advice. As a result, we propose a brand new solution to reuse experiences and transfer value functions among multiple students via model distillation. But it is still challenging to transfer Q-function directly si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02202","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/2002.02202/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":"2002.02202","created_at":"2026-07-05T00:38:50.216276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.02202v1","created_at":"2026-07-05T00:38:50.216276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02202","created_at":"2026-07-05T00:38:50.216276+00:00"},{"alias_kind":"pith_short_12","alias_value":"EVITA3C5B6MU","created_at":"2026-07-05T00:38:50.216276+00:00"},{"alias_kind":"pith_short_16","alias_value":"EVITA3C5B6MUQKHU","created_at":"2026-07-05T00:38:50.216276+00:00"},{"alias_kind":"pith_short_8","alias_value":"EVITA3C5","created_at":"2026-07-05T00:38:50.216276+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/EVITA3C5B6MUQKHUNMRNQQ7HXT","json":"https://pith.science/pith/EVITA3C5B6MUQKHUNMRNQQ7HXT.json","graph_json":"https://pith.science/api/pith-number/EVITA3C5B6MUQKHUNMRNQQ7HXT/graph.json","events_json":"https://pith.science/api/pith-number/EVITA3C5B6MUQKHUNMRNQQ7HXT/events.json","paper":"https://pith.science/paper/EVITA3C5"},"agent_actions":{"view_html":"https://pith.science/pith/EVITA3C5B6MUQKHUNMRNQQ7HXT","download_json":"https://pith.science/pith/EVITA3C5B6MUQKHUNMRNQQ7HXT.json","view_paper":"https://pith.science/paper/EVITA3C5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.02202&json=true","fetch_graph":"https://pith.science/api/pith-number/EVITA3C5B6MUQKHUNMRNQQ7HXT/graph.json","fetch_events":"https://pith.science/api/pith-number/EVITA3C5B6MUQKHUNMRNQQ7HXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EVITA3C5B6MUQKHUNMRNQQ7HXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EVITA3C5B6MUQKHUNMRNQQ7HXT/action/storage_attestation","attest_author":"https://pith.science/pith/EVITA3C5B6MUQKHUNMRNQQ7HXT/action/author_attestation","sign_citation":"https://pith.science/pith/EVITA3C5B6MUQKHUNMRNQQ7HXT/action/citation_signature","submit_replication":"https://pith.science/pith/EVITA3C5B6MUQKHUNMRNQQ7HXT/action/replication_record"}},"created_at":"2026-07-05T00:38:50.216276+00:00","updated_at":"2026-07-05T00:38:50.216276+00:00"}