{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AZRMENYDCIC6KIGIPGZYFC6P4B","short_pith_number":"pith:AZRMENYD","schema_version":"1.0","canonical_sha256":"0662c237031205e520c879b3828bcfe05ed83ca01848e8fb416d8c1fe32cc575","source":{"kind":"arxiv","id":"1803.08031","version":2},"attestation_state":"computed","paper":{"title":"Primal-Dual Algorithm for Distributed Reinforcement Learning: Distributed GTD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Donghwan Lee, Hyungjin Yoon, Naira Hovakimyan","submitted_at":"2018-03-21T17:46:45Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1803.08031","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-03-21T17:46:45Z","cross_cats_sorted":[],"title_canon_sha256":"08cf2504304e02462fbf29726548dd09d1e7cc64caa60397f8bfe110a6cf8aec","abstract_canon_sha256":"9b4fadd4b5e428b268a52def6295ff33d6545e296f209483634305389b1bf802"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:32.721287Z","signature_b64":"xu+mWuXkI8zseqthI609GMEoMolCgM3sEBAM5E0HqEhjpQn+FYmlVQQ1tksTdlHRom4m2WnrBjDwNqMWOeHSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0662c237031205e520c879b3828bcfe05ed83ca01848e8fb416d8c1fe32cc575","last_reissued_at":"2026-05-18T00:07:32.720532Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:32.720532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Primal-Dual Algorithm for Distributed Reinforcement Learning: Distributed GTD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Donghwan Lee, Hyungjin Yoon, Naira Hovakimyan","submitted_at":"2018-03-21T17:46:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08031","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1803.08031","created_at":"2026-05-18T00:07:32.720663+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.08031v2","created_at":"2026-05-18T00:07:32.720663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08031","created_at":"2026-05-18T00:07:32.720663+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZRMENYDCIC6","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZRMENYDCIC6KIGI","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZRMENYD","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B","json":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B.json","graph_json":"https://pith.science/api/pith-number/AZRMENYDCIC6KIGIPGZYFC6P4B/graph.json","events_json":"https://pith.science/api/pith-number/AZRMENYDCIC6KIGIPGZYFC6P4B/events.json","paper":"https://pith.science/paper/AZRMENYD"},"agent_actions":{"view_html":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B","download_json":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B.json","view_paper":"https://pith.science/paper/AZRMENYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.08031&json=true","fetch_graph":"https://pith.science/api/pith-number/AZRMENYDCIC6KIGIPGZYFC6P4B/graph.json","fetch_events":"https://pith.science/api/pith-number/AZRMENYDCIC6KIGIPGZYFC6P4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B/action/storage_attestation","attest_author":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B/action/author_attestation","sign_citation":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B/action/citation_signature","submit_replication":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B/action/replication_record"}},"created_at":"2026-05-18T00:07:32.720663+00:00","updated_at":"2026-05-18T00:07:32.720663+00:00"}