{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RKXHMCMDON2ZNTDFMLKQANROA4","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":"2b3dc98ed38bdeb4e10a81be5c454cc76d91d9f5f53c375cd7197f6e0561e8e0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T16:31:19Z","title_canon_sha256":"6d62a788df0eec91e342079e89b280c389708a5e2a95d3459fe62775dc70f1eb"},"schema_version":"1.0","source":{"id":"1812.06319","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.06319","created_at":"2026-07-05T01:10:10Z"},{"alias_kind":"arxiv_version","alias_value":"1812.06319v6","created_at":"2026-07-05T01:10:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06319","created_at":"2026-07-05T01:10:10Z"},{"alias_kind":"pith_short_12","alias_value":"RKXHMCMDON2Z","created_at":"2026-07-05T01:10:10Z"},{"alias_kind":"pith_short_16","alias_value":"RKXHMCMDON2ZNTDF","created_at":"2026-07-05T01:10:10Z"},{"alias_kind":"pith_short_8","alias_value":"RKXHMCMD","created_at":"2026-07-05T01:10:10Z"}],"graph_snapshots":[{"event_id":"sha256:3858b2f50500b63a0e5c3fb71d24c69e7cc4390f78ca46f8ca8aad5e8a802d7c","target":"graph","created_at":"2026-07-05T01:10:10Z","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/1812.06319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When multiple agents learn in a decentralized manner, the environment appears non-stationary from the perspective of an individual agent due to the exploration and learning of the other agents. Recently proposed deep multi-agent reinforcement learning methods have tried to mitigate this non-stationarity by attempting to determine which samples are from other agent exploration or suboptimality and take them less into account during learning. Based on the same philosophy, this paper introduces a decentralized quantile estimator, which aims to improve performance by distinguishing non-stationary ","authors_text":"Christopher Amato, Xueguang Lyu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T16:31:19Z","title":"Likelihood Quantile Networks for Coordinating Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06319","kind":"arxiv","version":6},"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":"sha256:405a87ce0af92aa1e361adc19aec23a23c8ebb041200f1243f22f9d405dd74ed","target":"record","created_at":"2026-07-05T01:10:10Z","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":"2b3dc98ed38bdeb4e10a81be5c454cc76d91d9f5f53c375cd7197f6e0561e8e0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T16:31:19Z","title_canon_sha256":"6d62a788df0eec91e342079e89b280c389708a5e2a95d3459fe62775dc70f1eb"},"schema_version":"1.0","source":{"id":"1812.06319","kind":"arxiv","version":6}},"canonical_sha256":"8aae760983737596cc6562d500362e073a745f16d7727939bfaf9d10dd3cbb0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8aae760983737596cc6562d500362e073a745f16d7727939bfaf9d10dd3cbb0e","first_computed_at":"2026-07-05T01:10:10.787426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:10.787426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pWsxHy70LGQsDpKT2aYuPfp3bVVZBiCoyzcjj/4DbbJWhU7xwdB3lRacvnOY4miGml39T8ppg92i8UtarS8zAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:10.787928Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.06319","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:405a87ce0af92aa1e361adc19aec23a23c8ebb041200f1243f22f9d405dd74ed","sha256:3858b2f50500b63a0e5c3fb71d24c69e7cc4390f78ca46f8ca8aad5e8a802d7c"],"state_sha256":"830ff631c13221cbecb486e7714fe44d491a572e79ddd8b11decad2154f36b0f"}