{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XF73FTNHTOA6SHC3BOQZ5BKK7I","short_pith_number":"pith:XF73FTNH","schema_version":"1.0","canonical_sha256":"b97fb2cda79b81e91c5b0ba19e854afa20d7099c2ceeed9edfdcd14d0354c9e0","source":{"kind":"arxiv","id":"2302.10418","version":2},"attestation_state":"computed","paper":{"title":"MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Guru Venkataramani, Hanhan Zhou, Peng Wei, Tian Lan, Yongsheng Mei","submitted_at":"2023-02-21T03:11:21Z","abstract_excerpt":"Experience replay is crucial for off-policy reinforcement learning (RL) methods. By remembering and reusing the experiences from past different policies, experience replay significantly improves the training efficiency and stability of RL algorithms. Many decision-making problems in practice naturally involve multiple agents and require multi-agent reinforcement learning (MARL) under centralized training decentralized execution paradigm. Nevertheless, existing MARL algorithms often adopt standard experience replay where the transitions are uniformly sampled regardless of their importance. Find"},"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":"2302.10418","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-21T03:11:21Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"3e0291df57f40c3aaccb5d8c239576e0ad3ba5188b7d8698bd093547b64cd788","abstract_canon_sha256":"c334ffac46469788e4b1f67cb7c95e339137dd1b8f2b77815695c97e5f9e6004"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:38.615482Z","signature_b64":"r4VHwdvYwA21GRb0K0gEjKzZeqWD7CUrExU/teGT1xdEcv2X30MoruV7F5qQ0k2LU5bMD6J5BZNvCLjelFpuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b97fb2cda79b81e91c5b0ba19e854afa20d7099c2ceeed9edfdcd14d0354c9e0","last_reissued_at":"2026-07-05T05:46:38.614987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:38.614987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Guru Venkataramani, Hanhan Zhou, Peng Wei, Tian Lan, Yongsheng Mei","submitted_at":"2023-02-21T03:11:21Z","abstract_excerpt":"Experience replay is crucial for off-policy reinforcement learning (RL) methods. By remembering and reusing the experiences from past different policies, experience replay significantly improves the training efficiency and stability of RL algorithms. Many decision-making problems in practice naturally involve multiple agents and require multi-agent reinforcement learning (MARL) under centralized training decentralized execution paradigm. Nevertheless, existing MARL algorithms often adopt standard experience replay where the transitions are uniformly sampled regardless of their importance. Find"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10418","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/2302.10418/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":"2302.10418","created_at":"2026-07-05T05:46:38.615046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.10418v2","created_at":"2026-07-05T05:46:38.615046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10418","created_at":"2026-07-05T05:46:38.615046+00:00"},{"alias_kind":"pith_short_12","alias_value":"XF73FTNHTOA6","created_at":"2026-07-05T05:46:38.615046+00:00"},{"alias_kind":"pith_short_16","alias_value":"XF73FTNHTOA6SHC3","created_at":"2026-07-05T05:46:38.615046+00:00"},{"alias_kind":"pith_short_8","alias_value":"XF73FTNH","created_at":"2026-07-05T05:46:38.615046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00751","citing_title":"NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XF73FTNHTOA6SHC3BOQZ5BKK7I","json":"https://pith.science/pith/XF73FTNHTOA6SHC3BOQZ5BKK7I.json","graph_json":"https://pith.science/api/pith-number/XF73FTNHTOA6SHC3BOQZ5BKK7I/graph.json","events_json":"https://pith.science/api/pith-number/XF73FTNHTOA6SHC3BOQZ5BKK7I/events.json","paper":"https://pith.science/paper/XF73FTNH"},"agent_actions":{"view_html":"https://pith.science/pith/XF73FTNHTOA6SHC3BOQZ5BKK7I","download_json":"https://pith.science/pith/XF73FTNHTOA6SHC3BOQZ5BKK7I.json","view_paper":"https://pith.science/paper/XF73FTNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.10418&json=true","fetch_graph":"https://pith.science/api/pith-number/XF73FTNHTOA6SHC3BOQZ5BKK7I/graph.json","fetch_events":"https://pith.science/api/pith-number/XF73FTNHTOA6SHC3BOQZ5BKK7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XF73FTNHTOA6SHC3BOQZ5BKK7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XF73FTNHTOA6SHC3BOQZ5BKK7I/action/storage_attestation","attest_author":"https://pith.science/pith/XF73FTNHTOA6SHC3BOQZ5BKK7I/action/author_attestation","sign_citation":"https://pith.science/pith/XF73FTNHTOA6SHC3BOQZ5BKK7I/action/citation_signature","submit_replication":"https://pith.science/pith/XF73FTNHTOA6SHC3BOQZ5BKK7I/action/replication_record"}},"created_at":"2026-07-05T05:46:38.615046+00:00","updated_at":"2026-07-05T05:46:38.615046+00:00"}