{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7LZIVHUIQXXAJU5KHAVP4EFYJB","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":"4dd96149f34ac0879b6a8cbef86f99f01055d3634b1e9c78ca21b0a1c8312205","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-03T02:21:07Z","title_canon_sha256":"ca7387096e54355619381b07271718f98cfb8d296fa2bff64bed41e0e7083348"},"schema_version":"1.0","source":{"id":"2004.01339","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.01339","created_at":"2026-07-05T00:57:52Z"},{"alias_kind":"arxiv_version","alias_value":"2004.01339v2","created_at":"2026-07-05T00:57:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.01339","created_at":"2026-07-05T00:57:52Z"},{"alias_kind":"pith_short_12","alias_value":"7LZIVHUIQXXA","created_at":"2026-07-05T00:57:52Z"},{"alias_kind":"pith_short_16","alias_value":"7LZIVHUIQXXAJU5K","created_at":"2026-07-05T00:57:52Z"},{"alias_kind":"pith_short_8","alias_value":"7LZIVHUI","created_at":"2026-07-05T00:57:52Z"}],"graph_snapshots":[{"event_id":"sha256:cee475f8c820be0fa7c7aad1c8a9f9ddf3715e91aefa74ccc3c61819204315db","target":"graph","created_at":"2026-07-05T00:57:52Z","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/2004.01339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper considers multi-agent reinforcement learning (MARL) in networked system control. Specifically, each agent learns a decentralized control policy based on local observations and messages from connected neighbors. We formulate such a networked MARL (NMARL) problem as a spatiotemporal Markov decision process and introduce a spatial discount factor to stabilize the training of each local agent. Further, we propose a new differentiable communication protocol, called NeurComm, to reduce information loss and non-stationarity in NMARL. Based on experiments in realistic NMARL scenarios of ada","authors_text":"Sachin Katti, Sandeep Chinchali, TianShu Chu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-03T02:21:07Z","title":"Multi-agent Reinforcement Learning for Networked System Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.01339","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":"sha256:0075d08db9d322a9cb95999c8aadc41d5ee9abaec885dec87224fce02e9d0320","target":"record","created_at":"2026-07-05T00:57:52Z","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":"4dd96149f34ac0879b6a8cbef86f99f01055d3634b1e9c78ca21b0a1c8312205","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-03T02:21:07Z","title_canon_sha256":"ca7387096e54355619381b07271718f98cfb8d296fa2bff64bed41e0e7083348"},"schema_version":"1.0","source":{"id":"2004.01339","kind":"arxiv","version":2}},"canonical_sha256":"faf28a9e8885ee04d3aa382afe10b84868a3497414fb6ead7b64b70b180d559c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"faf28a9e8885ee04d3aa382afe10b84868a3497414fb6ead7b64b70b180d559c","first_computed_at":"2026-07-05T00:57:52.875866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:57:52.875866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yL60f7sAOVEm8ylOJ7g+fBVUPhcjk9vd7ltOvYeaKjjByuFjP18Tp6/C5mNkVB42Wn/HruMIHElC0tscBKuwDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:57:52.876264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.01339","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0075d08db9d322a9cb95999c8aadc41d5ee9abaec885dec87224fce02e9d0320","sha256:cee475f8c820be0fa7c7aad1c8a9f9ddf3715e91aefa74ccc3c61819204315db"],"state_sha256":"d6ab083df7171f7d255a6e746541899f4869d14d23cb10d1d42341c65a6c4ed6"}