{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZP5T3QMITY7DXPQAX2ZUFY2BNA","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":"89b6dfa31f942aea901d470e0910c7ff72a415ef44428114c3a0e7dccf1790f2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T17:27:41Z","title_canon_sha256":"e2457b2895ac2c79406d93eff9ff458480d543a16a89067e0ed68777cd465d82"},"schema_version":"1.0","source":{"id":"1812.00922","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00922","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00922v1","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00922","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZP5T3QMITY7D","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZP5T3QMITY7DXPQA","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZP5T3QMI","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:cb42bbd5a98d4deb13f0e90ee8211459433f789c353206b07f8f4221c0c6a8ae","target":"graph","created_at":"2026-05-17T23:59:18Z","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":"Multi-agent reinforcement learning systems aim to provide interacting agents with the ability to collaboratively learn and adapt to the behaviour of other agents. In many real-world applications, the agents can only acquire a partial view of the world. Here we consider a setting whereby most agents' observations are also extremely noisy, hence only weakly correlated to the true state of the environment. Under these circumstances, learning an optimal policy becomes particularly challenging, even in the unrealistic case that an agent's policy can be made conditional upon all other agents' observ","authors_text":"Giovanni Montana, Ozsel Kilinc","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T17:27:41Z","title":"Multi-agent Deep Reinforcement Learning with Extremely Noisy Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00922","kind":"arxiv","version":1},"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":"sha256:0780322916b9515d5ab47e5f8abfc4c24a95e9babb53d0bbf5ff735d3bb1f0e8","target":"record","created_at":"2026-05-17T23:59:18Z","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":"89b6dfa31f942aea901d470e0910c7ff72a415ef44428114c3a0e7dccf1790f2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T17:27:41Z","title_canon_sha256":"e2457b2895ac2c79406d93eff9ff458480d543a16a89067e0ed68777cd465d82"},"schema_version":"1.0","source":{"id":"1812.00922","kind":"arxiv","version":1}},"canonical_sha256":"cbfb3dc1889e3e3bbe00beb342e341680684290cc100a2097828097844110c1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbfb3dc1889e3e3bbe00beb342e341680684290cc100a2097828097844110c1a","first_computed_at":"2026-05-17T23:59:18.590763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:18.590763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wpB2a+PBWT7IIuezoIPp/MKod7enanK+iShFXM7oyOwn71zAliiZMQQXL4HTfC6vXlDgt5jKbvipCuKLqCk2DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:18.591337Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.00922","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0780322916b9515d5ab47e5f8abfc4c24a95e9babb53d0bbf5ff735d3bb1f0e8","sha256:cb42bbd5a98d4deb13f0e90ee8211459433f789c353206b07f8f4221c0c6a8ae"],"state_sha256":"d04b4edcbcb3d0293afb35c363e7b6b88f59a5063a8b90db952f9fff62226d58"}