{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QPRW2DV45W2DP4TYY3WVJU5JEQ","short_pith_number":"pith:QPRW2DV4","canonical_record":{"source":{"id":"1802.08757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-23T22:53:32Z","cross_cats_sorted":["cs.AI","cs.MA","math.OC","stat.ML"],"title_canon_sha256":"d5ed6c4e131f82f729404c0ebe0d34b7a92945683f864aa2b11cbf2ac2c2e7ee","abstract_canon_sha256":"ee4e89ae3b6ff44ffe46f7904c1887e222efeb2fec27b42f240545b11ebda089"},"schema_version":"1.0"},"canonical_sha256":"83e36d0ebcedb437f278c6ed54d3a92425f14139f31949cc50a7d2e3a38a4368","source":{"kind":"arxiv","id":"1802.08757","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.08757","created_at":"2026-05-18T00:22:32Z"},{"alias_kind":"arxiv_version","alias_value":"1802.08757v2","created_at":"2026-05-18T00:22:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08757","created_at":"2026-05-18T00:22:32Z"},{"alias_kind":"pith_short_12","alias_value":"QPRW2DV45W2D","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QPRW2DV45W2DP4TY","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QPRW2DV4","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QPRW2DV45W2DP4TYY3WVJU5JEQ","target":"record","payload":{"canonical_record":{"source":{"id":"1802.08757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-23T22:53:32Z","cross_cats_sorted":["cs.AI","cs.MA","math.OC","stat.ML"],"title_canon_sha256":"d5ed6c4e131f82f729404c0ebe0d34b7a92945683f864aa2b11cbf2ac2c2e7ee","abstract_canon_sha256":"ee4e89ae3b6ff44ffe46f7904c1887e222efeb2fec27b42f240545b11ebda089"},"schema_version":"1.0"},"canonical_sha256":"83e36d0ebcedb437f278c6ed54d3a92425f14139f31949cc50a7d2e3a38a4368","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:32.953071Z","signature_b64":"6A8g2/Yt9wIvQEJveDGHS0ZiZ7TL+qqsHaVY5j8QocSwmeQv6bRcREhjIhCeV3sjUGPZAhbpGxsBidIo7f4DCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83e36d0ebcedb437f278c6ed54d3a92425f14139f31949cc50a7d2e3a38a4368","last_reissued_at":"2026-05-18T00:22:32.952592Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:32.952592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.08757","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":"2026-05-18T00:22:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FvyglPwng+mHeCWNdHLMjazpr5PfyxgM4T6PiwdA4u1rfQWRdiPOqTop6m9thX7ARbEaRNsSVHHlTlkJyU2/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T11:41:07.219649Z"},"content_sha256":"75362714bccb8a8617f4cbfa540b16d812fd16609f31a9ad3686632061196628","schema_version":"1.0","event_id":"sha256:75362714bccb8a8617f4cbfa540b16d812fd16609f31a9ad3686632061196628"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QPRW2DV45W2DP4TYY3WVJU5JEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Liu, Kaiqing Zhang, Tamer Ba\\c{s}ar, Tong Zhang, Zhuoran Yang","submitted_at":"2018-02-23T22:53:32Z","abstract_excerpt":"We consider the problem of \\emph{fully decentralized} multi-agent reinforcement learning (MARL), where the agents are located at the nodes of a time-varying communication network. Specifically, we assume that the reward functions of the agents might correspond to different tasks, and are only known to the corresponding agent. Moreover, each agent makes individual decisions based on both the information observed locally and the messages received from its neighbors over the network. Within this setting, the collective goal of the agents is to maximize the globally averaged return over the networ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08757","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":"2026-05-18T00:22:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SWvUFrXNw9IPXducGgi8uz1TbfE6kUbJ1mglXn5LN334LjGt0OSepIM3KWwnCC/BynQRqQcZSOFnM5UP4kN7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T11:41:07.220291Z"},"content_sha256":"ec2e27fc74be473a24baccde3c09192b4572bcf0b4e03551bb0d948fccbabe49","schema_version":"1.0","event_id":"sha256:ec2e27fc74be473a24baccde3c09192b4572bcf0b4e03551bb0d948fccbabe49"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QPRW2DV45W2DP4TYY3WVJU5JEQ/bundle.json","state_url":"https://pith.science/pith/QPRW2DV45W2DP4TYY3WVJU5JEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QPRW2DV45W2DP4TYY3WVJU5JEQ/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":"2026-06-08T11:41:07Z","links":{"resolver":"https://pith.science/pith/QPRW2DV45W2DP4TYY3WVJU5JEQ","bundle":"https://pith.science/pith/QPRW2DV45W2DP4TYY3WVJU5JEQ/bundle.json","state":"https://pith.science/pith/QPRW2DV45W2DP4TYY3WVJU5JEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QPRW2DV45W2DP4TYY3WVJU5JEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QPRW2DV45W2DP4TYY3WVJU5JEQ","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":"ee4e89ae3b6ff44ffe46f7904c1887e222efeb2fec27b42f240545b11ebda089","cross_cats_sorted":["cs.AI","cs.MA","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-23T22:53:32Z","title_canon_sha256":"d5ed6c4e131f82f729404c0ebe0d34b7a92945683f864aa2b11cbf2ac2c2e7ee"},"schema_version":"1.0","source":{"id":"1802.08757","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.08757","created_at":"2026-05-18T00:22:32Z"},{"alias_kind":"arxiv_version","alias_value":"1802.08757v2","created_at":"2026-05-18T00:22:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08757","created_at":"2026-05-18T00:22:32Z"},{"alias_kind":"pith_short_12","alias_value":"QPRW2DV45W2D","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QPRW2DV45W2DP4TY","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QPRW2DV4","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:ec2e27fc74be473a24baccde3c09192b4572bcf0b4e03551bb0d948fccbabe49","target":"graph","created_at":"2026-05-18T00:22:32Z","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":"We consider the problem of \\emph{fully decentralized} multi-agent reinforcement learning (MARL), where the agents are located at the nodes of a time-varying communication network. Specifically, we assume that the reward functions of the agents might correspond to different tasks, and are only known to the corresponding agent. Moreover, each agent makes individual decisions based on both the information observed locally and the messages received from its neighbors over the network. Within this setting, the collective goal of the agents is to maximize the globally averaged return over the networ","authors_text":"Han Liu, Kaiqing Zhang, Tamer Ba\\c{s}ar, Tong Zhang, Zhuoran Yang","cross_cats":["cs.AI","cs.MA","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-23T22:53:32Z","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08757","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":"sha256:75362714bccb8a8617f4cbfa540b16d812fd16609f31a9ad3686632061196628","target":"record","created_at":"2026-05-18T00:22:32Z","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":"ee4e89ae3b6ff44ffe46f7904c1887e222efeb2fec27b42f240545b11ebda089","cross_cats_sorted":["cs.AI","cs.MA","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-23T22:53:32Z","title_canon_sha256":"d5ed6c4e131f82f729404c0ebe0d34b7a92945683f864aa2b11cbf2ac2c2e7ee"},"schema_version":"1.0","source":{"id":"1802.08757","kind":"arxiv","version":2}},"canonical_sha256":"83e36d0ebcedb437f278c6ed54d3a92425f14139f31949cc50a7d2e3a38a4368","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83e36d0ebcedb437f278c6ed54d3a92425f14139f31949cc50a7d2e3a38a4368","first_computed_at":"2026-05-18T00:22:32.952592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:32.952592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6A8g2/Yt9wIvQEJveDGHS0ZiZ7TL+qqsHaVY5j8QocSwmeQv6bRcREhjIhCeV3sjUGPZAhbpGxsBidIo7f4DCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:32.953071Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.08757","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75362714bccb8a8617f4cbfa540b16d812fd16609f31a9ad3686632061196628","sha256:ec2e27fc74be473a24baccde3c09192b4572bcf0b4e03551bb0d948fccbabe49"],"state_sha256":"3214627e2cc591728f81cfffe7211bbc24a3c1b99f36c298184216807dc9cef0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xu2c5OxOJMqmVZkUjhgmUMb0oBcC/xuhqR71j52XUeUpmsq/wxM/Ynr5WPcHROR8NlwM5Fpo5yG4IiCkY6cZBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T11:41:07.223968Z","bundle_sha256":"a65a96f539fa9e3025499d1bf302c81e516e6641049a478418ae64887f594624"}}