{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XF73FTNHTOA6SHC3BOQZ5BKK7I","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":"c334ffac46469788e4b1f67cb7c95e339137dd1b8f2b77815695c97e5f9e6004","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-21T03:11:21Z","title_canon_sha256":"3e0291df57f40c3aaccb5d8c239576e0ad3ba5188b7d8698bd093547b64cd788"},"schema_version":"1.0","source":{"id":"2302.10418","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10418","created_at":"2026-07-05T05:46:38Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10418v2","created_at":"2026-07-05T05:46:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10418","created_at":"2026-07-05T05:46:38Z"},{"alias_kind":"pith_short_12","alias_value":"XF73FTNHTOA6","created_at":"2026-07-05T05:46:38Z"},{"alias_kind":"pith_short_16","alias_value":"XF73FTNHTOA6SHC3","created_at":"2026-07-05T05:46:38Z"},{"alias_kind":"pith_short_8","alias_value":"XF73FTNH","created_at":"2026-07-05T05:46:38Z"}],"graph_snapshots":[{"event_id":"sha256:5225848377b50d2bc57bc884f39ce1945e613ff884da0f5e145aad080ed83a67","target":"graph","created_at":"2026-07-05T05:46:38Z","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/2302.10418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guru Venkataramani, Hanhan Zhou, Peng Wei, Tian Lan, Yongsheng Mei","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-21T03:11:21Z","title":"MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10418","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":"sha256:830c934fb7639af0247c70b76c4a0783c488a995985a280a8c51098ed422af67","target":"record","created_at":"2026-07-05T05:46:38Z","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":"c334ffac46469788e4b1f67cb7c95e339137dd1b8f2b77815695c97e5f9e6004","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-21T03:11:21Z","title_canon_sha256":"3e0291df57f40c3aaccb5d8c239576e0ad3ba5188b7d8698bd093547b64cd788"},"schema_version":"1.0","source":{"id":"2302.10418","kind":"arxiv","version":2}},"canonical_sha256":"b97fb2cda79b81e91c5b0ba19e854afa20d7099c2ceeed9edfdcd14d0354c9e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b97fb2cda79b81e91c5b0ba19e854afa20d7099c2ceeed9edfdcd14d0354c9e0","first_computed_at":"2026-07-05T05:46:38.614987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:46:38.614987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r4VHwdvYwA21GRb0K0gEjKzZeqWD7CUrExU/teGT1xdEcv2X30MoruV7F5qQ0k2LU5bMD6J5BZNvCLjelFpuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:46:38.615482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.10418","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:830c934fb7639af0247c70b76c4a0783c488a995985a280a8c51098ed422af67","sha256:5225848377b50d2bc57bc884f39ce1945e613ff884da0f5e145aad080ed83a67"],"state_sha256":"c65c8e3a2da5e78081526f95c653887b4d1255d0c816485d7d39b1f2b53328c1"}