{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4RRM4ZJAAS77XZO2SNKR5KRDMJ","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":"f4117c2325c33c59b8cce24e37155f6bf8843d3392f7e008d8f477e255c471c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-21T06:56:04Z","title_canon_sha256":"00d5f781078490e656d19d24ca7e13e29701e427a4e2d8050c8c3416156bc7a8"},"schema_version":"1.0","source":{"id":"1805.07918","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07918","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07918v6","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07918","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"pith_short_12","alias_value":"4RRM4ZJAAS77","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"pith_short_16","alias_value":"4RRM4ZJAAS77XZO2","created_at":"2026-07-05T00:58:30Z"},{"alias_kind":"pith_short_8","alias_value":"4RRM4ZJA","created_at":"2026-07-05T00:58:30Z"}],"graph_snapshots":[{"event_id":"sha256:52c8a59e9e2794ad69085a0392f03b1ab7bf4ccd52aa36eebc4d44778edb3cee","target":"graph","created_at":"2026-07-05T00:58:30Z","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/1805.07918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for a class of multi-agent Markov decision processes (MDPs). The temporal-difference (TD) learning is a reinforcement learning (RL) algorithm that learns an infinite horizon discounted cost function (or value function) for a given fixed policy without the model knowledge. In the multi-agent MDP each agent receives a local reward through a local processing. The agents communicate over sparse and random networks to learn the global value function corresponding to the aggregate of","authors_text":"Donghwan Lee, Jianghai Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-21T06:56:04Z","title":"Primal-Dual Distributed Temporal Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07918","kind":"arxiv","version":6},"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":"sha256:8e6c25c54cae2619fdee84a1879ff78f5f38d71fadebb5e3bf96ce8c32961626","target":"record","created_at":"2026-07-05T00:58:30Z","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":"f4117c2325c33c59b8cce24e37155f6bf8843d3392f7e008d8f477e255c471c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-21T06:56:04Z","title_canon_sha256":"00d5f781078490e656d19d24ca7e13e29701e427a4e2d8050c8c3416156bc7a8"},"schema_version":"1.0","source":{"id":"1805.07918","kind":"arxiv","version":6}},"canonical_sha256":"e462ce652004bffbe5da93551eaa23626be4f3a427d906b1c1b3ea1a210891eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e462ce652004bffbe5da93551eaa23626be4f3a427d906b1c1b3ea1a210891eb","first_computed_at":"2026-07-05T00:58:30.668214Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:58:30.668214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w9P1csuMoZTCSq7JV/y56OvKMcHguNjzJGp6iSbKA6C6P2yHkWyF0WIuxQu6ynLhpxP+8iFWHo6F1xTgu2cUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:58:30.668809Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07918","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e6c25c54cae2619fdee84a1879ff78f5f38d71fadebb5e3bf96ce8c32961626","sha256:52c8a59e9e2794ad69085a0392f03b1ab7bf4ccd52aa36eebc4d44778edb3cee"],"state_sha256":"966e2a1e89060e7bed859fdebfa33bf6c216c897474e79e0ce26643711cd0099"}