{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6Z4LJS3SY7KQI54URPKDUJRTAE","short_pith_number":"pith:6Z4LJS3S","canonical_record":{"source":{"id":"2006.06555","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T16:08:16Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"c123555fa423dbac4a70442ab31e31f371c3a33dcdab4da5d050fa680c6d0258","abstract_canon_sha256":"3406ff40f55ed12f3d1d9e1aa2f891547834558db477008b9e9d3294bc160d95"},"schema_version":"1.0"},"canonical_sha256":"f678b4cb72c7d50477948bd43a26330137023ed690eea1319409eeb0c4baff6e","source":{"kind":"arxiv","id":"2006.06555","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06555","created_at":"2026-07-05T03:27:54Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06555v3","created_at":"2026-07-05T03:27:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06555","created_at":"2026-07-05T03:27:54Z"},{"alias_kind":"pith_short_12","alias_value":"6Z4LJS3SY7KQ","created_at":"2026-07-05T03:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"6Z4LJS3SY7KQI54U","created_at":"2026-07-05T03:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"6Z4LJS3S","created_at":"2026-07-05T03:27:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6Z4LJS3SY7KQI54URPKDUJRTAE","target":"record","payload":{"canonical_record":{"source":{"id":"2006.06555","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T16:08:16Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"c123555fa423dbac4a70442ab31e31f371c3a33dcdab4da5d050fa680c6d0258","abstract_canon_sha256":"3406ff40f55ed12f3d1d9e1aa2f891547834558db477008b9e9d3294bc160d95"},"schema_version":"1.0"},"canonical_sha256":"f678b4cb72c7d50477948bd43a26330137023ed690eea1319409eeb0c4baff6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:54.782179Z","signature_b64":"4f2h1DZXWgvn9P5B35z3brRk32UfvtMam35gosa/+l1v4okm086zk7ykAv17kdFj+cB3YOSAssDmGyc+3DpgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f678b4cb72c7d50477948bd43a26330137023ed690eea1319409eeb0c4baff6e","last_reissued_at":"2026-07-05T03:27:54.781816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:54.781816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.06555","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:27:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6UXvIUX5FCdiUvaTgBLrU2pwqd0EJ/8Mbtyxh0d2AiCkoSag1dB3YaG/odDtn9QNdQXwec+i1vd+NRvh0CfhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:22:22.397563Z"},"content_sha256":"f88fbbadf8a0e31315a9ee9fd23b112d401d62d723efc45f5088060799490138","schema_version":"1.0","event_id":"sha256:f88fbbadf8a0e31315a9ee9fd23b112d401d62d723efc45f5088060799490138"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6Z4LJS3SY7KQI54URPKDUJRTAE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning in Stochastic Networked Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Guannan Qu, Longbo Huang, Yiheng Lin","submitted_at":"2020-06-11T16:08:16Z","abstract_excerpt":"We study multi-agent reinforcement learning (MARL) in a stochastic network of agents. The objective is to find localized policies that maximize the (discounted) global reward. In general, scalability is a challenge in this setting because the size of the global state/action space can be exponential in the number of agents. Scalable algorithms are only known in cases where dependencies are static, fixed and local, e.g., between neighbors in a fixed, time-invariant underlying graph. In this work, we propose a Scalable Actor Critic framework that applies in settings where the dependencies can be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06555","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.06555/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T03:27:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rRhLO8rpekuEvwflOOMmHCk0mUjXlthCHJmqVyLnTNJPpR7OeRoL5z6qmVnRnUtpzIjzdzDGeckbolvBXXRPCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:22:22.398608Z"},"content_sha256":"a0af32d26a1122ed97b1743bdd192d1765726fdbf58653b481695355d3beeaa4","schema_version":"1.0","event_id":"sha256:a0af32d26a1122ed97b1743bdd192d1765726fdbf58653b481695355d3beeaa4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6Z4LJS3SY7KQI54URPKDUJRTAE/bundle.json","state_url":"https://pith.science/pith/6Z4LJS3SY7KQI54URPKDUJRTAE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6Z4LJS3SY7KQI54URPKDUJRTAE/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":"2026-08-17T20:22:22Z","links":{"resolver":"https://pith.science/pith/6Z4LJS3SY7KQI54URPKDUJRTAE","bundle":"https://pith.science/pith/6Z4LJS3SY7KQI54URPKDUJRTAE/bundle.json","state":"https://pith.science/pith/6Z4LJS3SY7KQI54URPKDUJRTAE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6Z4LJS3SY7KQI54URPKDUJRTAE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6Z4LJS3SY7KQI54URPKDUJRTAE","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":"3406ff40f55ed12f3d1d9e1aa2f891547834558db477008b9e9d3294bc160d95","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T16:08:16Z","title_canon_sha256":"c123555fa423dbac4a70442ab31e31f371c3a33dcdab4da5d050fa680c6d0258"},"schema_version":"1.0","source":{"id":"2006.06555","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06555","created_at":"2026-07-05T03:27:54Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06555v3","created_at":"2026-07-05T03:27:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06555","created_at":"2026-07-05T03:27:54Z"},{"alias_kind":"pith_short_12","alias_value":"6Z4LJS3SY7KQ","created_at":"2026-07-05T03:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"6Z4LJS3SY7KQI54U","created_at":"2026-07-05T03:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"6Z4LJS3S","created_at":"2026-07-05T03:27:54Z"}],"graph_snapshots":[{"event_id":"sha256:a0af32d26a1122ed97b1743bdd192d1765726fdbf58653b481695355d3beeaa4","target":"graph","created_at":"2026-07-05T03:27:54Z","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/2006.06555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study multi-agent reinforcement learning (MARL) in a stochastic network of agents. The objective is to find localized policies that maximize the (discounted) global reward. In general, scalability is a challenge in this setting because the size of the global state/action space can be exponential in the number of agents. Scalable algorithms are only known in cases where dependencies are static, fixed and local, e.g., between neighbors in a fixed, time-invariant underlying graph. In this work, we propose a Scalable Actor Critic framework that applies in settings where the dependencies can be ","authors_text":"Adam Wierman, Guannan Qu, Longbo Huang, Yiheng Lin","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T16:08:16Z","title":"Multi-Agent Reinforcement Learning in Stochastic Networked Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06555","kind":"arxiv","version":3},"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:f88fbbadf8a0e31315a9ee9fd23b112d401d62d723efc45f5088060799490138","target":"record","created_at":"2026-07-05T03:27:54Z","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":"3406ff40f55ed12f3d1d9e1aa2f891547834558db477008b9e9d3294bc160d95","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T16:08:16Z","title_canon_sha256":"c123555fa423dbac4a70442ab31e31f371c3a33dcdab4da5d050fa680c6d0258"},"schema_version":"1.0","source":{"id":"2006.06555","kind":"arxiv","version":3}},"canonical_sha256":"f678b4cb72c7d50477948bd43a26330137023ed690eea1319409eeb0c4baff6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f678b4cb72c7d50477948bd43a26330137023ed690eea1319409eeb0c4baff6e","first_computed_at":"2026-07-05T03:27:54.781816Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:54.781816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4f2h1DZXWgvn9P5B35z3brRk32UfvtMam35gosa/+l1v4okm086zk7ykAv17kdFj+cB3YOSAssDmGyc+3DpgBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:54.782179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.06555","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f88fbbadf8a0e31315a9ee9fd23b112d401d62d723efc45f5088060799490138","sha256:a0af32d26a1122ed97b1743bdd192d1765726fdbf58653b481695355d3beeaa4"],"state_sha256":"0cdad63539f1400aa55c9bb1c7bea3e82bca2b10bbf8ce2df5d268dff8ebef57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8efr5QjtWtEn+xwpWnEM2raHT2gj6TNAP/u4gy/81spej4h/VqqYPEbN0u1V3jGqYxFUjbtB+5FyGSqGMB3qBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:22:22.407123Z","bundle_sha256":"0594546f678c0cf4fb495c632906b62e232ccdb494e6409f6403e2231dab5d0b"}}