{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KNPWDHJSWG4Z3OBD7PXXJX3C5S","short_pith_number":"pith:KNPWDHJS","schema_version":"1.0","canonical_sha256":"535f619d32b1b99db823fbef74df62ec88aac13b331cd2a2f9e689f29aede9bc","source":{"kind":"arxiv","id":"2311.00865","version":2},"attestation_state":"computed","paper":{"title":"Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.RO"],"primary_cat":"cs.LG","authors_text":"Matthias Gerstgrasser, Sarah Keren, Tom Danino","submitted_at":"2023-11-01T21:35:32Z","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"},"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":"2311.00865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T21:35:32Z","cross_cats_sorted":["cs.AI","cs.MA","cs.RO"],"title_canon_sha256":"765912c19030f4ae83225bb45acb7ce5f128f8731f4955157fb4a8f26a204613","abstract_canon_sha256":"9592517361b7284a9a1a92162d975e1d5a4010a4bfe7a5d1e650b2e0152b20ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:21.238752Z","signature_b64":"oqjD4AJBuckVKix/pT13J+YSkPoEdfWehi5qyk671uXFF5PHokNtLDJAn18BpjIkPV+0x/pNccO+swzQDjeSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"535f619d32b1b99db823fbef74df62ec88aac13b331cd2a2f9e689f29aede9bc","last_reissued_at":"2026-07-05T08:11:21.238278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:21.238278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.RO"],"primary_cat":"cs.LG","authors_text":"Matthias Gerstgrasser, Sarah Keren, Tom Danino","submitted_at":"2023-11-01T21:35:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00865","kind":"arxiv","version":2},"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/2311.00865/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":"2311.00865","created_at":"2026-07-05T08:11:21.238341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00865v2","created_at":"2026-07-05T08:11:21.238341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00865","created_at":"2026-07-05T08:11:21.238341+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNPWDHJSWG4Z","created_at":"2026-07-05T08:11:21.238341+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNPWDHJSWG4Z3OBD","created_at":"2026-07-05T08:11:21.238341+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNPWDHJS","created_at":"2026-07-05T08:11:21.238341+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/KNPWDHJSWG4Z3OBD7PXXJX3C5S","json":"https://pith.science/pith/KNPWDHJSWG4Z3OBD7PXXJX3C5S.json","graph_json":"https://pith.science/api/pith-number/KNPWDHJSWG4Z3OBD7PXXJX3C5S/graph.json","events_json":"https://pith.science/api/pith-number/KNPWDHJSWG4Z3OBD7PXXJX3C5S/events.json","paper":"https://pith.science/paper/KNPWDHJS"},"agent_actions":{"view_html":"https://pith.science/pith/KNPWDHJSWG4Z3OBD7PXXJX3C5S","download_json":"https://pith.science/pith/KNPWDHJSWG4Z3OBD7PXXJX3C5S.json","view_paper":"https://pith.science/paper/KNPWDHJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00865&json=true","fetch_graph":"https://pith.science/api/pith-number/KNPWDHJSWG4Z3OBD7PXXJX3C5S/graph.json","fetch_events":"https://pith.science/api/pith-number/KNPWDHJSWG4Z3OBD7PXXJX3C5S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNPWDHJSWG4Z3OBD7PXXJX3C5S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNPWDHJSWG4Z3OBD7PXXJX3C5S/action/storage_attestation","attest_author":"https://pith.science/pith/KNPWDHJSWG4Z3OBD7PXXJX3C5S/action/author_attestation","sign_citation":"https://pith.science/pith/KNPWDHJSWG4Z3OBD7PXXJX3C5S/action/citation_signature","submit_replication":"https://pith.science/pith/KNPWDHJSWG4Z3OBD7PXXJX3C5S/action/replication_record"}},"created_at":"2026-07-05T08:11:21.238341+00:00","updated_at":"2026-07-05T08:11:21.238341+00:00"}