{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RTTREJWAZM4RZGJHYJDRGAPVNU","short_pith_number":"pith:RTTREJWA","schema_version":"1.0","canonical_sha256":"8ce71226c0cb391c9927c2471301f56d2eef6f1459bf7c2ae234ea4a6ccbbf64","source":{"kind":"arxiv","id":"2411.10459","version":1},"attestation_state":"computed","paper":{"title":"Evolutionary Multi-agent Reinforcement Learning in Group Social Dilemmas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.PE"],"primary_cat":"cs.MA","authors_text":"Brian Mintz, Feng Fu","submitted_at":"2024-11-01T19:46:08Z","abstract_excerpt":"Reinforcement learning (RL) is a powerful machine learning technique that has been successfully applied to a wide variety of problems. However, it can be unpredictable and produce suboptimal results in complicated learning environments. This is especially true when multiple agents learn simultaneously, which creates a complex system that is often analytically intractable. Our work considers the fundamental framework of Q-learning in Public Goods Games, where RL individuals must work together to achieve a common goal. This setting allows us to study the tragedy of the commons and free rider eff"},"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":"2411.10459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-11-01T19:46:08Z","cross_cats_sorted":["q-bio.PE"],"title_canon_sha256":"af55bebbba3cd7ecdd667b9289d03fbe1d5f591139587ceb2f8707a87d68babe","abstract_canon_sha256":"db23ad02eeb25caf83d824a6845c3875f98a28244eb3b854d83bbc89068c40ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:17.006993Z","signature_b64":"wLmQPbHbIjz29CRWqy8R25xaCD1r5Kt787rwisptukpHTcvIkv3nWnnts+uy4CB8CAcqGleNhaLvO3sAI7qhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ce71226c0cb391c9927c2471301f56d2eef6f1459bf7c2ae234ea4a6ccbbf64","last_reissued_at":"2026-07-05T09:36:17.006489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:17.006489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evolutionary Multi-agent Reinforcement Learning in Group Social Dilemmas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.PE"],"primary_cat":"cs.MA","authors_text":"Brian Mintz, Feng Fu","submitted_at":"2024-11-01T19:46:08Z","abstract_excerpt":"Reinforcement learning (RL) is a powerful machine learning technique that has been successfully applied to a wide variety of problems. However, it can be unpredictable and produce suboptimal results in complicated learning environments. This is especially true when multiple agents learn simultaneously, which creates a complex system that is often analytically intractable. Our work considers the fundamental framework of Q-learning in Public Goods Games, where RL individuals must work together to achieve a common goal. This setting allows us to study the tragedy of the commons and free rider eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10459","kind":"arxiv","version":1},"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/2411.10459/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":"2411.10459","created_at":"2026-07-05T09:36:17.006546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10459v1","created_at":"2026-07-05T09:36:17.006546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10459","created_at":"2026-07-05T09:36:17.006546+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTTREJWAZM4R","created_at":"2026-07-05T09:36:17.006546+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTTREJWAZM4RZGJH","created_at":"2026-07-05T09:36:17.006546+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTTREJWA","created_at":"2026-07-05T09:36:17.006546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00160","citing_title":"Deterministic Model of Incremental Multi-Agent Boltzmann Q-Learning: Transient Cooperation, Metastability, and Oscillations","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTTREJWAZM4RZGJHYJDRGAPVNU","json":"https://pith.science/pith/RTTREJWAZM4RZGJHYJDRGAPVNU.json","graph_json":"https://pith.science/api/pith-number/RTTREJWAZM4RZGJHYJDRGAPVNU/graph.json","events_json":"https://pith.science/api/pith-number/RTTREJWAZM4RZGJHYJDRGAPVNU/events.json","paper":"https://pith.science/paper/RTTREJWA"},"agent_actions":{"view_html":"https://pith.science/pith/RTTREJWAZM4RZGJHYJDRGAPVNU","download_json":"https://pith.science/pith/RTTREJWAZM4RZGJHYJDRGAPVNU.json","view_paper":"https://pith.science/paper/RTTREJWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10459&json=true","fetch_graph":"https://pith.science/api/pith-number/RTTREJWAZM4RZGJHYJDRGAPVNU/graph.json","fetch_events":"https://pith.science/api/pith-number/RTTREJWAZM4RZGJHYJDRGAPVNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTTREJWAZM4RZGJHYJDRGAPVNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTTREJWAZM4RZGJHYJDRGAPVNU/action/storage_attestation","attest_author":"https://pith.science/pith/RTTREJWAZM4RZGJHYJDRGAPVNU/action/author_attestation","sign_citation":"https://pith.science/pith/RTTREJWAZM4RZGJHYJDRGAPVNU/action/citation_signature","submit_replication":"https://pith.science/pith/RTTREJWAZM4RZGJHYJDRGAPVNU/action/replication_record"}},"created_at":"2026-07-05T09:36:17.006546+00:00","updated_at":"2026-07-05T09:36:17.006546+00:00"}