{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:W46MUNBGZ7PIQVTUMLVDGHISQ6","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":"f12c2de34dbc46ec5a4c70658c0110ecae162b1b3859c1ee35fbc366735b3286","cross_cats_sorted":["cs.GT","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-21T14:46:50Z","title_canon_sha256":"5d17dca0991d2ffba8b9f48be0060f30ee5be08a3bfee213e2eed4228f5cae92"},"schema_version":"1.0","source":{"id":"2102.10616","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10616","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10616v2","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10616","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"W46MUNBGZ7PI","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"pith_short_16","alias_value":"W46MUNBGZ7PIQVTU","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"pith_short_8","alias_value":"W46MUNBG","created_at":"2026-07-05T03:55:47Z"}],"graph_snapshots":[{"event_id":"sha256:1f877dc2b3899eac634847ca9423772afc1a8014dc2198c9f23a602ce48923af","target":"graph","created_at":"2026-07-05T03:55:47Z","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/2102.10616/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Non-stationarity is one thorny issue in cooperative multi-agent reinforcement learning (MARL). One of the reasons is the policy changes of agents during the learning process. Some existing works have discussed various consequences caused by non-stationarity with several kinds of measurement indicators. This makes the objectives or goals of existing algorithms are inevitably inconsistent and disparate. In this paper, we introduce a novel notion, the $\\delta$-measurement, to explicitly measure the non-stationarity of a policy sequence, which can be further proved to be bounded by the KL-divergen","authors_text":"Bo Jin, Hongyuan Zha, Junjie Sheng, Wenhao Li, Xiangfeng Wang","cross_cats":["cs.GT","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-21T14:46:50Z","title":"Dealing with Non-Stationarity in MARL via Trust-Region Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10616","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":"sha256:476e28ee27f9d8266a2e6145f08df4d484839a9324172a12f118ef4c47257c3f","target":"record","created_at":"2026-07-05T03:55:47Z","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":"f12c2de34dbc46ec5a4c70658c0110ecae162b1b3859c1ee35fbc366735b3286","cross_cats_sorted":["cs.GT","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-21T14:46:50Z","title_canon_sha256":"5d17dca0991d2ffba8b9f48be0060f30ee5be08a3bfee213e2eed4228f5cae92"},"schema_version":"1.0","source":{"id":"2102.10616","kind":"arxiv","version":2}},"canonical_sha256":"b73cca3426cfde88567462ea331d12878b2c74528141e825cf1dfcd4e636b542","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b73cca3426cfde88567462ea331d12878b2c74528141e825cf1dfcd4e636b542","first_computed_at":"2026-07-05T03:55:47.095129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:55:47.095129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sd5xhFGUYwSr2F58/3mLuuLVOiwCds653QlzbFwZsEssN0dCOtcsu/8QrVKl86vlNWqdCMIN3PNZh8Z8GUP/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:55:47.095665Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.10616","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:476e28ee27f9d8266a2e6145f08df4d484839a9324172a12f118ef4c47257c3f","sha256:1f877dc2b3899eac634847ca9423772afc1a8014dc2198c9f23a602ce48923af"],"state_sha256":"19014d5fdf77dd9c9ecf77966d1765aec046f4dc2cd4006530646cda7c539ba6"}