{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5ICJFADO44MQ3VKUTMGEPCEV2Q","short_pith_number":"pith:5ICJFADO","schema_version":"1.0","canonical_sha256":"ea0492806ee7190dd5549b0c478895d42f8fe524664339bae264b890e2917150","source":{"kind":"arxiv","id":"2410.18636","version":2},"attestation_state":"computed","paper":{"title":"Multi-agent cooperation through learning-aware policy gradients","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","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","submitted_at":"2024-10-24T10:48:42Z","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"},"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":"2410.18636","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-24T10:48:42Z","cross_cats_sorted":[],"title_canon_sha256":"21569197ada4a70d8b6ce7455257b4102b555d7fa6b14d68acf6eb06b0bf11ec","abstract_canon_sha256":"ff9eaf46082e101830653ad1a3c9a944a944e6e11092e3caac19f7e0534cbc5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:40.850746Z","signature_b64":"GdLpEQMU2K9ezhBjHv+lNSqKZJgIX6+niL9+udlAhuJ1gv2HCHiTY0MZ+dtqFGGiTI+bE2OjLWBelcbpa0RhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea0492806ee7190dd5549b0c478895d42f8fe524664339bae264b890e2917150","last_reissued_at":"2026-07-05T10:34:40.850226Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:40.850226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-agent cooperation through learning-aware policy gradients","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","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","submitted_at":"2024-10-24T10:48:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18636","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/2410.18636/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":"2410.18636","created_at":"2026-07-05T10:34:40.850294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18636v2","created_at":"2026-07-05T10:34:40.850294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18636","created_at":"2026-07-05T10:34:40.850294+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ICJFADO44MQ","created_at":"2026-07-05T10:34:40.850294+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ICJFADO44MQ3VKU","created_at":"2026-07-05T10:34:40.850294+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ICJFADO","created_at":"2026-07-05T10:34:40.850294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20579","citing_title":"The challenge of hidden gifts in multi-agent reinforcement learning","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ICJFADO44MQ3VKUTMGEPCEV2Q","json":"https://pith.science/pith/5ICJFADO44MQ3VKUTMGEPCEV2Q.json","graph_json":"https://pith.science/api/pith-number/5ICJFADO44MQ3VKUTMGEPCEV2Q/graph.json","events_json":"https://pith.science/api/pith-number/5ICJFADO44MQ3VKUTMGEPCEV2Q/events.json","paper":"https://pith.science/paper/5ICJFADO"},"agent_actions":{"view_html":"https://pith.science/pith/5ICJFADO44MQ3VKUTMGEPCEV2Q","download_json":"https://pith.science/pith/5ICJFADO44MQ3VKUTMGEPCEV2Q.json","view_paper":"https://pith.science/paper/5ICJFADO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18636&json=true","fetch_graph":"https://pith.science/api/pith-number/5ICJFADO44MQ3VKUTMGEPCEV2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/5ICJFADO44MQ3VKUTMGEPCEV2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ICJFADO44MQ3VKUTMGEPCEV2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ICJFADO44MQ3VKUTMGEPCEV2Q/action/storage_attestation","attest_author":"https://pith.science/pith/5ICJFADO44MQ3VKUTMGEPCEV2Q/action/author_attestation","sign_citation":"https://pith.science/pith/5ICJFADO44MQ3VKUTMGEPCEV2Q/action/citation_signature","submit_replication":"https://pith.science/pith/5ICJFADO44MQ3VKUTMGEPCEV2Q/action/replication_record"}},"created_at":"2026-07-05T10:34:40.850294+00:00","updated_at":"2026-07-05T10:34:40.850294+00:00"}