{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KNPWDHJSWG4Z3OBD7PXXJX3C5S","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":"9592517361b7284a9a1a92162d975e1d5a4010a4bfe7a5d1e650b2e0152b20ec","cross_cats_sorted":["cs.AI","cs.MA","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T21:35:32Z","title_canon_sha256":"765912c19030f4ae83225bb45acb7ce5f128f8731f4955157fb4a8f26a204613"},"schema_version":"1.0","source":{"id":"2311.00865","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00865","created_at":"2026-07-05T08:11:21Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00865v2","created_at":"2026-07-05T08:11:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00865","created_at":"2026-07-05T08:11:21Z"},{"alias_kind":"pith_short_12","alias_value":"KNPWDHJSWG4Z","created_at":"2026-07-05T08:11:21Z"},{"alias_kind":"pith_short_16","alias_value":"KNPWDHJSWG4Z3OBD","created_at":"2026-07-05T08:11:21Z"},{"alias_kind":"pith_short_8","alias_value":"KNPWDHJS","created_at":"2026-07-05T08:11:21Z"}],"graph_snapshots":[{"event_id":"sha256:731f7eb48574f1ba8542def03277a30ad5cc6877b674a3711ff996afb704fb5a","target":"graph","created_at":"2026-07-05T08:11:21Z","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/2311.00865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel multi-agent RL approach, Selective Multi-Agent Prioritized Experience Relay, in which agents share with other agents a limited number of transitions they observe during training. The intuition behind this is that even a small number of relevant experiences from other agents could help each agent learn. Unlike many other multi-agent RL algorithms, this approach allows for largely decentralized training, requiring only a limited communication channel between agents. We show that our approach outperforms baseline no-sharing decentralized training and state-of-the art multi-agen","authors_text":"Matthias Gerstgrasser, Sarah Keren, Tom Danino","cross_cats":["cs.AI","cs.MA","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T21:35:32Z","title":"Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00865","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:a48ee7584e3b68e0f4b67928dd42616c00298734f099ad02e1a5d5d7a950f31c","target":"record","created_at":"2026-07-05T08:11:21Z","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":"9592517361b7284a9a1a92162d975e1d5a4010a4bfe7a5d1e650b2e0152b20ec","cross_cats_sorted":["cs.AI","cs.MA","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T21:35:32Z","title_canon_sha256":"765912c19030f4ae83225bb45acb7ce5f128f8731f4955157fb4a8f26a204613"},"schema_version":"1.0","source":{"id":"2311.00865","kind":"arxiv","version":2}},"canonical_sha256":"535f619d32b1b99db823fbef74df62ec88aac13b331cd2a2f9e689f29aede9bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"535f619d32b1b99db823fbef74df62ec88aac13b331cd2a2f9e689f29aede9bc","first_computed_at":"2026-07-05T08:11:21.238278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:21.238278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oqjD4AJBuckVKix/pT13J+YSkPoEdfWehi5qyk671uXFF5PHokNtLDJAn18BpjIkPV+0x/pNccO+swzQDjeSCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:21.238752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00865","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a48ee7584e3b68e0f4b67928dd42616c00298734f099ad02e1a5d5d7a950f31c","sha256:731f7eb48574f1ba8542def03277a30ad5cc6877b674a3711ff996afb704fb5a"],"state_sha256":"bcffd3bf0b001ac5d44e9d057e31db484949e374ad5b509bf2b9ee110118cca8"}