{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NGA7ZE2IQZ32XSMZJWP3R45MPH","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":"8169dfa3358d52d2ef2c022cbf0bd3c3c9267f807c773135dd4b0b269f445dc2","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-31T22:50:21Z","title_canon_sha256":"01ec36756db417bd40da4f7c51263aa7c2cf17f34d5def723648f72c00028c64"},"schema_version":"1.0","source":{"id":"2011.00382","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.00382","created_at":"2026-07-05T02:48:34Z"},{"alias_kind":"arxiv_version","alias_value":"2011.00382v5","created_at":"2026-07-05T02:48:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.00382","created_at":"2026-07-05T02:48:34Z"},{"alias_kind":"pith_short_12","alias_value":"NGA7ZE2IQZ32","created_at":"2026-07-05T02:48:34Z"},{"alias_kind":"pith_short_16","alias_value":"NGA7ZE2IQZ32XSMZ","created_at":"2026-07-05T02:48:34Z"},{"alias_kind":"pith_short_8","alias_value":"NGA7ZE2I","created_at":"2026-07-05T02:48:34Z"}],"graph_snapshots":[{"event_id":"sha256:af4b87a84be099b01015ef7b0191d2c173e6f98e1e91aa1321a38e365137d39e","target":"graph","created_at":"2026-07-05T02:48:34Z","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/2011.00382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effectively non-stationary due to the changing policies of other agents. Moreover, each agent is itself constantly learning, leading to natural non-stationarity in the distribution of experiences encountered. In this paper, we propose a novel meta-multiagent policy gradient theorem that directly accounts for the non-stationary policy dynamics inherent to multiagent learning setting","authors_text":"Chuangchuang Sun, Dong-Ki Kim, Gerald Tesauro, Golnaz Habibi, Jonathan P. How, Marwa Abdulhai, Matthew Riemer, Miao Liu, Sebastian Lopez-Cot","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-31T22:50:21Z","title":"A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.00382","kind":"arxiv","version":5},"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":"sha256:1125ed78df3c035a123ef7a3c9356cb8bfbd86de3f763bf7ead15db6d675c9de","target":"record","created_at":"2026-07-05T02:48:34Z","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":"8169dfa3358d52d2ef2c022cbf0bd3c3c9267f807c773135dd4b0b269f445dc2","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-31T22:50:21Z","title_canon_sha256":"01ec36756db417bd40da4f7c51263aa7c2cf17f34d5def723648f72c00028c64"},"schema_version":"1.0","source":{"id":"2011.00382","kind":"arxiv","version":5}},"canonical_sha256":"6981fc93488677abc9994d9fb8f3ac79e31771ae0e58118da78fe9e84a0a8f67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6981fc93488677abc9994d9fb8f3ac79e31771ae0e58118da78fe9e84a0a8f67","first_computed_at":"2026-07-05T02:48:34.672385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:34.672385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WjgK8mN+9XZAdc1/iktEYuieYHqLOv//nqenr9bQZM8zPJoLiInIVAL7c8FJ2EuHiY72d3It6d7Bx1uvvMrTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:34.672849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.00382","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1125ed78df3c035a123ef7a3c9356cb8bfbd86de3f763bf7ead15db6d675c9de","sha256:af4b87a84be099b01015ef7b0191d2c173e6f98e1e91aa1321a38e365137d39e"],"state_sha256":"f42d6683965584be88862e4c4e27f39383c20a1a4a0e4e639c6aa5a9d4f80ffb"}