{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EVITA3C5B6MUQKHUNMRNQQ7HXT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4d1ed2fcafdbc701eb9c03c846c335a9f9b74b75a53233456c8454c49fbcb1f0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-02-06T11:31:04Z","title_canon_sha256":"9c443ce041ee0a4c5dec019a265798b0d223ddb8cd320e0570f41e53cde95a06"},"schema_version":"1.0","source":{"id":"2002.02202","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.02202","created_at":"2026-07-05T00:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2002.02202v1","created_at":"2026-07-05T00:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02202","created_at":"2026-07-05T00:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"EVITA3C5B6MU","created_at":"2026-07-05T00:38:50Z"},{"alias_kind":"pith_short_16","alias_value":"EVITA3C5B6MUQKHU","created_at":"2026-07-05T00:38:50Z"},{"alias_kind":"pith_short_8","alias_value":"EVITA3C5","created_at":"2026-07-05T00:38:50Z"}],"graph_snapshots":[{"event_id":"sha256:f1f235856cea97746154ecdc08c9eb5ab26149fb589ff5767e5e774b8f49d313","target":"graph","created_at":"2026-07-05T00:38:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.02202/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chao Wu, Kaigui Bian, Pan Zhou, Shuang Luo, Wei Du, Zeyue Xue","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-02-06T11:31:04Z","title":"Transfer Heterogeneous Knowledge Among Peer-to-Peer Teammates: A Model Distillation Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02202","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:25c4390ca931ba9bc46f3019c8b48ba57beb637d8bca7d9d570695e685f24357","target":"record","created_at":"2026-07-05T00:38:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4d1ed2fcafdbc701eb9c03c846c335a9f9b74b75a53233456c8454c49fbcb1f0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-02-06T11:31:04Z","title_canon_sha256":"9c443ce041ee0a4c5dec019a265798b0d223ddb8cd320e0570f41e53cde95a06"},"schema_version":"1.0","source":{"id":"2002.02202","kind":"arxiv","version":1}},"canonical_sha256":"2551306c5d0f994828f46b22d843e7bccb1e7fd9320a72178d761f7e88883598","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2551306c5d0f994828f46b22d843e7bccb1e7fd9320a72178d761f7e88883598","first_computed_at":"2026-07-05T00:38:50.216211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:38:50.216211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lrf9anVh0f5vLpDO5qsqtWeQBxhCf9JLOULPWiHlT7vIMZZ8YOxUdPDrNaZ1e4U7d3acABE3EhYj2Tnu57Y/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:38:50.216618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.02202","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25c4390ca931ba9bc46f3019c8b48ba57beb637d8bca7d9d570695e685f24357","sha256:f1f235856cea97746154ecdc08c9eb5ab26149fb589ff5767e5e774b8f49d313"],"state_sha256":"2e60f84bb23f7fd837207baeb953d3e79105e8dac7ec88f6366fc8d9d252326e"}