{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BAZEMAHTUC36KK7HM7AHAXWRE3","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":"f6d2b4cdb755b39d4639ff9d3ca689f8919952716d411eed89e1b94d7a3df6a3","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-31T07:58:52Z","title_canon_sha256":"f83b9b04d35516686f17f417152985b2dd88b272b234f417be09d9f15afaee67"},"schema_version":"1.0","source":{"id":"2304.00977","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00977","created_at":"2026-07-05T09:28:27Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00977v2","created_at":"2026-07-05T09:28:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00977","created_at":"2026-07-05T09:28:27Z"},{"alias_kind":"pith_short_12","alias_value":"BAZEMAHTUC36","created_at":"2026-07-05T09:28:27Z"},{"alias_kind":"pith_short_16","alias_value":"BAZEMAHTUC36KK7H","created_at":"2026-07-05T09:28:27Z"},{"alias_kind":"pith_short_8","alias_value":"BAZEMAHT","created_at":"2026-07-05T09:28:27Z"}],"graph_snapshots":[{"event_id":"sha256:06ffdc933bcbdb771fa8bdb96b574015813e94d8d0500a4b96127c17046338fa","target":"graph","created_at":"2026-07-05T09:28:27Z","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/2304.00977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"'Reincarnation' in reinforcement learning has been proposed as a formalisation of reusing prior computation from past experiments when training an agent in an environment. In this paper, we present a brief foray into the paradigm of reincarnation in the multi-agent (MA) context. We consider the case where only some agents are reincarnated, whereas the others are trained from scratch -- selective reincarnation. In the fully-cooperative MA setting with heterogeneous agents, we demonstrate that selective reincarnation can lead to higher returns than training fully from scratch, and faster converg","authors_text":"Arnu Pretorius, Callum Rhys Tilbury, Claude Formanek, Jonathan Shock, Kale-ab Tessera","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-31T07:58:52Z","title":"Selective Reincarnation: Offline-to-Online Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00977","kind":"arxiv","version":2},"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":"sha256:7208259d4e667c7c35d145aced30bba4041ed8bf80ce271aeb3f3c39e6b5a2c8","target":"record","created_at":"2026-07-05T09:28:27Z","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":"f6d2b4cdb755b39d4639ff9d3ca689f8919952716d411eed89e1b94d7a3df6a3","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-31T07:58:52Z","title_canon_sha256":"f83b9b04d35516686f17f417152985b2dd88b272b234f417be09d9f15afaee67"},"schema_version":"1.0","source":{"id":"2304.00977","kind":"arxiv","version":2}},"canonical_sha256":"08324600f3a0b7e52be767c0705ed126fe6d2e5626d4ac08c3278491c88fe1ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08324600f3a0b7e52be767c0705ed126fe6d2e5626d4ac08c3278491c88fe1ab","first_computed_at":"2026-07-05T09:28:27.044347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:27.044347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"whDqrERaaK6oHCPKo9j8eoMJBi3vRBF0NA0dPp5CTZPz8oVY/192WLL7FzwBwJN6rE1J0GG8RZaUfuxvH75dBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:27.044780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.00977","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7208259d4e667c7c35d145aced30bba4041ed8bf80ce271aeb3f3c39e6b5a2c8","sha256:06ffdc933bcbdb771fa8bdb96b574015813e94d8d0500a4b96127c17046338fa"],"state_sha256":"d8d503ece8ada838fa20f9eed4d00ad010228b339cb83703bd4a36ca56571ead"}