{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CMGRGBZWDPDDVWFMRYYSYK5GDG","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":"12fa18f5e8637085c4de7656afb5f73ab8b5eb6eb418de505bda078df2b82b80","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-23T21:39:56Z","title_canon_sha256":"97ffab2c75482f8f16bf5af262e799ba86b8b8fbe20b7364bea2a802cfad7da1"},"schema_version":"1.0","source":{"id":"2403.15935","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.15935","created_at":"2026-07-05T08:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"2403.15935v1","created_at":"2026-07-05T08:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15935","created_at":"2026-07-05T08:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"CMGRGBZWDPDD","created_at":"2026-07-05T08:00:08Z"},{"alias_kind":"pith_short_16","alias_value":"CMGRGBZWDPDDVWFM","created_at":"2026-07-05T08:00:08Z"},{"alias_kind":"pith_short_8","alias_value":"CMGRGBZW","created_at":"2026-07-05T08:00:08Z"}],"graph_snapshots":[{"event_id":"sha256:958bce78b87ed960e068b8b0e7a18e71e54d87f5ca735df8e6cebd5d62b08c96","target":"graph","created_at":"2026-07-05T08:00:08Z","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/2403.15935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In actor-critic framework for fully decentralized multi-agent reinforcement learning (MARL), one of the key components is the MARL policy evaluation (PE) problem, where a set of $N$ agents work cooperatively to evaluate the value function of the global states for a given policy through communicating with their neighbors. In MARL-PE, a critical challenge is how to lower the sample and communication complexities, which are defined as the number of training samples and communication rounds needed to converge to some $\\epsilon$-stationary point. To lower communication complexity in MARL-PE, a \"nat","authors_text":"Fnu Hairi, Jia Liu, Zifan Zhang","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-23T21:39:56Z","title":"Sample and Communication Efficient Fully Decentralized MARL Policy Evaluation via a New Approach: Local TD update"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15935","kind":"arxiv","version":1},"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":"sha256:583beb0d1091dde990d4f15bbc83749c9639d224130332d3a797e20bf52e0937","target":"record","created_at":"2026-07-05T08:00:08Z","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":"12fa18f5e8637085c4de7656afb5f73ab8b5eb6eb418de505bda078df2b82b80","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-23T21:39:56Z","title_canon_sha256":"97ffab2c75482f8f16bf5af262e799ba86b8b8fbe20b7364bea2a802cfad7da1"},"schema_version":"1.0","source":{"id":"2403.15935","kind":"arxiv","version":1}},"canonical_sha256":"130d1307361bc63ad8ac8e312c2ba6199100a6079e28c6e7af5527d08a4bbcd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"130d1307361bc63ad8ac8e312c2ba6199100a6079e28c6e7af5527d08a4bbcd5","first_computed_at":"2026-07-05T08:00:08.592262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:08.592262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kgqLZaqoHbF4ifRqjWeGHWfatIMf60JNXyDdXqkK5Gg5g9eJEe8z+D/9cB/kFF0PFfewjF2/TXqLcIPObvRVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:08.592780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.15935","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:583beb0d1091dde990d4f15bbc83749c9639d224130332d3a797e20bf52e0937","sha256:958bce78b87ed960e068b8b0e7a18e71e54d87f5ca735df8e6cebd5d62b08c96"],"state_sha256":"6016159ff908b3af147096a609374fe1f4f54c5f49793bcda6cc7922cd9ecff4"}