{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5ICJFADO44MQ3VKUTMGEPCEV2Q","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":"ff9eaf46082e101830653ad1a3c9a944a944e6e11092e3caac19f7e0534cbc5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-24T10:48:42Z","title_canon_sha256":"21569197ada4a70d8b6ce7455257b4102b555d7fa6b14d68acf6eb06b0bf11ec"},"schema_version":"1.0","source":{"id":"2410.18636","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18636","created_at":"2026-07-05T10:34:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18636v2","created_at":"2026-07-05T10:34:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18636","created_at":"2026-07-05T10:34:40Z"},{"alias_kind":"pith_short_12","alias_value":"5ICJFADO44MQ","created_at":"2026-07-05T10:34:40Z"},{"alias_kind":"pith_short_16","alias_value":"5ICJFADO44MQ3VKU","created_at":"2026-07-05T10:34:40Z"},{"alias_kind":"pith_short_8","alias_value":"5ICJFADO","created_at":"2026-07-05T10:34:40Z"}],"graph_snapshots":[{"event_id":"sha256:cb23532b397fb361c2cac49b873d290414d5a4e2b3262ad8a0b0f35f350b6a5d","target":"graph","created_at":"2026-07-05T10:34:40Z","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/2410.18636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-interested individuals often fail to cooperate, posing a fundamental challenge for multi-agent learning. How can we achieve cooperation among self-interested, independent learning agents? Promising recent work has shown that in certain tasks cooperation can be established between learning-aware agents who model the learning dynamics of each other. Here, we present the first unbiased, higher-derivative-free policy gradient algorithm for learning-aware reinforcement learning, which takes into account that other agents are themselves learning through trial and error based on multiple noisy t","authors_text":"Alexander Meulemans, Blaise Ag\\\"uera y Arcas, Blake Richards, Eric Elmoznino, Guillaume Lajoie, Jo\\~ao Sacramento, Johannes von Oswald, Nino Scherrer, Seijin Kobayashi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-24T10:48:42Z","title":"Multi-agent cooperation through learning-aware policy gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18636","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":"sha256:776898c25b7aec205ed8618ad588736bab5fac911e8fcdb65431a7308f64e529","target":"record","created_at":"2026-07-05T10:34:40Z","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":"ff9eaf46082e101830653ad1a3c9a944a944e6e11092e3caac19f7e0534cbc5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-24T10:48:42Z","title_canon_sha256":"21569197ada4a70d8b6ce7455257b4102b555d7fa6b14d68acf6eb06b0bf11ec"},"schema_version":"1.0","source":{"id":"2410.18636","kind":"arxiv","version":2}},"canonical_sha256":"ea0492806ee7190dd5549b0c478895d42f8fe524664339bae264b890e2917150","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea0492806ee7190dd5549b0c478895d42f8fe524664339bae264b890e2917150","first_computed_at":"2026-07-05T10:34:40.850226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:40.850226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GdLpEQMU2K9ezhBjHv+lNSqKZJgIX6+niL9+udlAhuJ1gv2HCHiTY0MZ+dtqFGGiTI+bE2OjLWBelcbpa0RhBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:40.850746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18636","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:776898c25b7aec205ed8618ad588736bab5fac911e8fcdb65431a7308f64e529","sha256:cb23532b397fb361c2cac49b873d290414d5a4e2b3262ad8a0b0f35f350b6a5d"],"state_sha256":"c20780b5870490abb6a1d95820d05479ee7e5a434c20e52bb8e6efd0d8823355"}