{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AZRMENYDCIC6KIGIPGZYFC6P4B","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":"9b4fadd4b5e428b268a52def6295ff33d6545e296f209483634305389b1bf802","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-03-21T17:46:45Z","title_canon_sha256":"08cf2504304e02462fbf29726548dd09d1e7cc64caa60397f8bfe110a6cf8aec"},"schema_version":"1.0","source":{"id":"1803.08031","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.08031","created_at":"2026-05-18T00:07:32Z"},{"alias_kind":"arxiv_version","alias_value":"1803.08031v2","created_at":"2026-05-18T00:07:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08031","created_at":"2026-05-18T00:07:32Z"},{"alias_kind":"pith_short_12","alias_value":"AZRMENYDCIC6","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AZRMENYDCIC6KIGI","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AZRMENYD","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:f9b843012194c4fa4c2859f82b0ab045ba721d2371c8cd7f6e79da2b2a3e563f","target":"graph","created_at":"2026-05-18T00:07:32Z","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"},"paper":{"abstract_excerpt":"The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for multi-agent Markov decision processes (MDPs). The temporal difference (TD) learning is a reinforcement learning (RL) algorithm which learns an infinite horizon discounted cost function (or value function) for a given fixed policy without the model knowledge. In the distributed RL case each agent receives local reward through a local processing. Information exchange over sparse communication network allows the agents to learn the global value function corresponding to a glob","authors_text":"Donghwan Lee, Hyungjin Yoon, Naira Hovakimyan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-03-21T17:46:45Z","title":"Primal-Dual Algorithm for Distributed Reinforcement Learning: Distributed GTD"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08031","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":"sha256:4bb1c72295031d3aac3e990a0b5286099c8f2cc7a9ecf05175c690a448f37e1d","target":"record","created_at":"2026-05-18T00:07:32Z","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":"9b4fadd4b5e428b268a52def6295ff33d6545e296f209483634305389b1bf802","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-03-21T17:46:45Z","title_canon_sha256":"08cf2504304e02462fbf29726548dd09d1e7cc64caa60397f8bfe110a6cf8aec"},"schema_version":"1.0","source":{"id":"1803.08031","kind":"arxiv","version":2}},"canonical_sha256":"0662c237031205e520c879b3828bcfe05ed83ca01848e8fb416d8c1fe32cc575","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0662c237031205e520c879b3828bcfe05ed83ca01848e8fb416d8c1fe32cc575","first_computed_at":"2026-05-18T00:07:32.720532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:32.720532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xu+mWuXkI8zseqthI609GMEoMolCgM3sEBAM5E0HqEhjpQn+FYmlVQQ1tksTdlHRom4m2WnrBjDwNqMWOeHSCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:32.721287Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.08031","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bb1c72295031d3aac3e990a0b5286099c8f2cc7a9ecf05175c690a448f37e1d","sha256:f9b843012194c4fa4c2859f82b0ab045ba721d2371c8cd7f6e79da2b2a3e563f"],"state_sha256":"af37a3744c3debfd51ae2927412084d0e5fc7d4d050aa263f8b0ee6465d1f3cf"}