{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3GNNUP6GEGWDOZKJDWHWINJ4P5","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":"008ee362480649294cc79674f8f037228b0eafaa508079ab33a9a33717fcb596","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T20:39:48Z","title_canon_sha256":"9a652730fd2a2950f2a29694aca180a44ee236eb46250d609f04790602ebdb0a"},"schema_version":"1.0","source":{"id":"2202.00082","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00082","created_at":"2026-07-05T05:42:00Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00082v3","created_at":"2026-07-05T05:42:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00082","created_at":"2026-07-05T05:42:00Z"},{"alias_kind":"pith_short_12","alias_value":"3GNNUP6GEGWD","created_at":"2026-07-05T05:42:00Z"},{"alias_kind":"pith_short_16","alias_value":"3GNNUP6GEGWDOZKJ","created_at":"2026-07-05T05:42:00Z"},{"alias_kind":"pith_short_8","alias_value":"3GNNUP6G","created_at":"2026-07-05T05:42:00Z"}],"graph_snapshots":[{"event_id":"sha256:428bdccc9b2d4adb498d55b6bd5d8cd24378b774d1317553cc3065c8d4adef3b","target":"graph","created_at":"2026-07-05T05:42:00Z","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/2202.00082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present trust region bounds for optimizing decentralized policies in cooperative Multi-Agent Reinforcement Learning (MARL), which holds even when the transition dynamics are non-stationary. This new analysis provides a theoretical understanding of the strong performance of two recent actor-critic methods for MARL, which both rely on independent ratios, i.e., computing probability ratios separately for each agent's policy. We show that, despite the non-stationarity that independent ratios cause, a monotonic improvement guarantee still arises as a result of enforcing the trust region constrai","authors_text":"Jacob Beck, Katja Hofmann, Mingfei Sun, Sam Devlin, Shimon Whiteson","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T20:39:48Z","title":"Trust Region Bounds for Decentralized PPO Under Non-stationarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00082","kind":"arxiv","version":3},"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":"sha256:7eaf468208f3dcedb26d3c18bbfc80f5f4c71bab8708c3bca69307ac1dcb034a","target":"record","created_at":"2026-07-05T05:42:00Z","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":"008ee362480649294cc79674f8f037228b0eafaa508079ab33a9a33717fcb596","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T20:39:48Z","title_canon_sha256":"9a652730fd2a2950f2a29694aca180a44ee236eb46250d609f04790602ebdb0a"},"schema_version":"1.0","source":{"id":"2202.00082","kind":"arxiv","version":3}},"canonical_sha256":"d99ada3fc621ac3765491d8f64353c7f66f3d96add8ed5ab3215a23a5bfd3cdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d99ada3fc621ac3765491d8f64353c7f66f3d96add8ed5ab3215a23a5bfd3cdf","first_computed_at":"2026-07-05T05:42:00.525700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:42:00.525700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P9niFxXo0O+lNrm1lKdMSS0lSR8u0tdT6IfEYN9U3F9jK2+Wy97n5Lkesu4tSLDnUhSl7s9GtrDs1ImHrcEhAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:42:00.526197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.00082","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eaf468208f3dcedb26d3c18bbfc80f5f4c71bab8708c3bca69307ac1dcb034a","sha256:428bdccc9b2d4adb498d55b6bd5d8cd24378b774d1317553cc3065c8d4adef3b"],"state_sha256":"8ce1695121da5926f30a6c365e8ce517616976e26adee36bb3a254330064ac41"}