{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:W46MUNBGZ7PIQVTUMLVDGHISQ6","short_pith_number":"pith:W46MUNBG","schema_version":"1.0","canonical_sha256":"b73cca3426cfde88567462ea331d12878b2c74528141e825cf1dfcd4e636b542","source":{"kind":"arxiv","id":"2102.10616","version":2},"attestation_state":"computed","paper":{"title":"Dealing with Non-Stationarity in MARL via Trust-Region Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Bo Jin, Hongyuan Zha, Junjie Sheng, Wenhao Li, Xiangfeng Wang","submitted_at":"2021-02-21T14:46:50Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2102.10616","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-21T14:46:50Z","cross_cats_sorted":["cs.GT","cs.MA"],"title_canon_sha256":"5d17dca0991d2ffba8b9f48be0060f30ee5be08a3bfee213e2eed4228f5cae92","abstract_canon_sha256":"f12c2de34dbc46ec5a4c70658c0110ecae162b1b3859c1ee35fbc366735b3286"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:55:47.095665Z","signature_b64":"sd5xhFGUYwSr2F58/3mLuuLVOiwCds653QlzbFwZsEssN0dCOtcsu/8QrVKl86vlNWqdCMIN3PNZh8Z8GUP/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b73cca3426cfde88567462ea331d12878b2c74528141e825cf1dfcd4e636b542","last_reissued_at":"2026-07-05T03:55:47.095129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:55:47.095129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dealing with Non-Stationarity in MARL via Trust-Region Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Bo Jin, Hongyuan Zha, Junjie Sheng, Wenhao Li, Xiangfeng Wang","submitted_at":"2021-02-21T14:46:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10616","kind":"arxiv","version":2},"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/2102.10616/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2102.10616","created_at":"2026-07-05T03:55:47.095200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.10616v2","created_at":"2026-07-05T03:55:47.095200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10616","created_at":"2026-07-05T03:55:47.095200+00:00"},{"alias_kind":"pith_short_12","alias_value":"W46MUNBGZ7PI","created_at":"2026-07-05T03:55:47.095200+00:00"},{"alias_kind":"pith_short_16","alias_value":"W46MUNBGZ7PIQVTU","created_at":"2026-07-05T03:55:47.095200+00:00"},{"alias_kind":"pith_short_8","alias_value":"W46MUNBG","created_at":"2026-07-05T03:55:47.095200+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W46MUNBGZ7PIQVTUMLVDGHISQ6","json":"https://pith.science/pith/W46MUNBGZ7PIQVTUMLVDGHISQ6.json","graph_json":"https://pith.science/api/pith-number/W46MUNBGZ7PIQVTUMLVDGHISQ6/graph.json","events_json":"https://pith.science/api/pith-number/W46MUNBGZ7PIQVTUMLVDGHISQ6/events.json","paper":"https://pith.science/paper/W46MUNBG"},"agent_actions":{"view_html":"https://pith.science/pith/W46MUNBGZ7PIQVTUMLVDGHISQ6","download_json":"https://pith.science/pith/W46MUNBGZ7PIQVTUMLVDGHISQ6.json","view_paper":"https://pith.science/paper/W46MUNBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.10616&json=true","fetch_graph":"https://pith.science/api/pith-number/W46MUNBGZ7PIQVTUMLVDGHISQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/W46MUNBGZ7PIQVTUMLVDGHISQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W46MUNBGZ7PIQVTUMLVDGHISQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W46MUNBGZ7PIQVTUMLVDGHISQ6/action/storage_attestation","attest_author":"https://pith.science/pith/W46MUNBGZ7PIQVTUMLVDGHISQ6/action/author_attestation","sign_citation":"https://pith.science/pith/W46MUNBGZ7PIQVTUMLVDGHISQ6/action/citation_signature","submit_replication":"https://pith.science/pith/W46MUNBGZ7PIQVTUMLVDGHISQ6/action/replication_record"}},"created_at":"2026-07-05T03:55:47.095200+00:00","updated_at":"2026-07-05T03:55:47.095200+00:00"}