{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:AZRMENYDCIC6KIGIPGZYFC6P4B","short_pith_number":"pith:AZRMENYD","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"},"canonical_sha256":"0662c237031205e520c879b3828bcfe05ed83ca01848e8fb416d8c1fe32cc575","source":{"kind":"arxiv","id":"1803.08031","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:AZRMENYDCIC6KIGIPGZYFC6P4B","target":"record","payload":{"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"},"canonical_sha256":"0662c237031205e520c879b3828bcfe05ed83ca01848e8fb416d8c1fe32cc575","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"},"source_kind":"arxiv","source_id":"1803.08031","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wCCdiVAMszjwaF6tGSBLiZQTZURgbGLqMVT4O8DzJjduRpOT+84XF/7Htu6qSFdGDW34Y+UJvFgT87EDF/EeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T05:42:07.332452Z"},"content_sha256":"4bb1c72295031d3aac3e990a0b5286099c8f2cc7a9ecf05175c690a448f37e1d","schema_version":"1.0","event_id":"sha256:4bb1c72295031d3aac3e990a0b5286099c8f2cc7a9ecf05175c690a448f37e1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:AZRMENYDCIC6KIGIPGZYFC6P4B","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jvbBKMYi6NGty+l3WVNmt001ZEgVmEFMoyZYsIgiBrUNsXwbjRsBGv/aGa8ohyvEYRknqJDjnOois6SwjiNmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T05:42:07.332868Z"},"content_sha256":"f9b843012194c4fa4c2859f82b0ab045ba721d2371c8cd7f6e79da2b2a3e563f","schema_version":"1.0","event_id":"sha256:f9b843012194c4fa4c2859f82b0ab045ba721d2371c8cd7f6e79da2b2a3e563f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B/bundle.json","state_url":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZRMENYDCIC6KIGIPGZYFC6P4B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T05:42:07Z","links":{"resolver":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B","bundle":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B/bundle.json","state":"https://pith.science/pith/AZRMENYDCIC6KIGIPGZYFC6P4B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZRMENYDCIC6KIGIPGZYFC6P4B/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Dt9u0V+dtfQ9MsINBEC3hLX73wPvl+JT++9t9wY1OiL+LEKfr0a+zy+OMReTx1GTwk+XibXkBirRGfdh7P4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T05:42:07.335429Z","bundle_sha256":"f44535cadee96029dcfe950772fdc6dddc1816d45b65e4968b9994d53716cd16"}}