{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IKL7SKEJIES3ZSLEWI4QDMDLGQ","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":"c0b1af448e10a51816ba64f31106b2199eae8b3df92eb758b984749cbd77bdf4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-07-25T18:32:43Z","title_canon_sha256":"9552bfb807603b8abedcad57a86f402cdaf7deca1fc7666948a0c43d6233fff8"},"schema_version":"1.0","source":{"id":"1907.12530","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.12530","created_at":"2026-07-05T00:32:38Z"},{"alias_kind":"arxiv_version","alias_value":"1907.12530v2","created_at":"2026-07-05T00:32:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.12530","created_at":"2026-07-05T00:32:38Z"},{"alias_kind":"pith_short_12","alias_value":"IKL7SKEJIES3","created_at":"2026-07-05T00:32:38Z"},{"alias_kind":"pith_short_16","alias_value":"IKL7SKEJIES3ZSLE","created_at":"2026-07-05T00:32:38Z"},{"alias_kind":"pith_short_8","alias_value":"IKL7SKEJ","created_at":"2026-07-05T00:32:38Z"}],"graph_snapshots":[{"event_id":"sha256:436473ca58d524be0c7a0f0720f75985a637d969038231ea0f65f1ea2bf5096e","target":"graph","created_at":"2026-07-05T00:32:38Z","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/1907.12530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the policy evaluation problem in multi-agent reinforcement learning, modeled by a Markov decision process. In this problem, the agents operate in a common environment under a fixed control policy, working together to discover the value (global discounted accumulative reward) associated with each environmental state. Over a series of time steps, the agents act, get rewarded, update their local estimate of the value function, then communicate with their neighbors. The local update at each agent can be interpreted as a distributed variant of the popular temporal difference learning metho","authors_text":"Justin Romberg, Siva Theja Maguluri, Thinh T. Doan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-07-25T18:32:43Z","title":"Finite-Time Performance of Distributed Temporal Difference Learning with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12530","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":"sha256:8daa0ec2d6621c3b6bf272bdb9eb6468eb2334c73815b1f53c1de260bd9eee6a","target":"record","created_at":"2026-07-05T00:32:38Z","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":"c0b1af448e10a51816ba64f31106b2199eae8b3df92eb758b984749cbd77bdf4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-07-25T18:32:43Z","title_canon_sha256":"9552bfb807603b8abedcad57a86f402cdaf7deca1fc7666948a0c43d6233fff8"},"schema_version":"1.0","source":{"id":"1907.12530","kind":"arxiv","version":2}},"canonical_sha256":"4297f928894125bcc964b23901b06b343bf2c8bb8112e92d011a0d4fd760943e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4297f928894125bcc964b23901b06b343bf2c8bb8112e92d011a0d4fd760943e","first_computed_at":"2026-07-05T00:32:38.870190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:32:38.870190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RHs+lv4VR00y4mg7vf7PU1IrWyp5CnaR2MoZjmW2U6ddi91msPCOrJSPUijmXg710EZb2aTCBtXxcId2WEgABQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:32:38.870715Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.12530","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8daa0ec2d6621c3b6bf272bdb9eb6468eb2334c73815b1f53c1de260bd9eee6a","sha256:436473ca58d524be0c7a0f0720f75985a637d969038231ea0f65f1ea2bf5096e"],"state_sha256":"98bf228e650691cfca4c89c43ea6183c9c3634a9996ac859163d4c7be2b954b6"}