{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GEXKKWNGMLMV7IONEL6J5HLSGS","short_pith_number":"pith:GEXKKWNG","schema_version":"1.0","canonical_sha256":"312ea559a662d95fa1cd22fc9e9d723482136cd14c3f9d6376ffe926ce90190f","source":{"kind":"arxiv","id":"1803.00162","version":1},"attestation_state":"computed","paper":{"title":"Towards Cooperation in Sequential Prisoner's Dilemmas: a Deep Multiagent Reinforcement Learning Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Jianye Hao, Matthew Taylor, Weixun Wang, Yixi Wang","submitted_at":"2018-03-01T01:53:52Z","abstract_excerpt":"The Iterated Prisoner's Dilemma has guided research on social dilemmas for decades. However, it distinguishes between only two atomic actions: cooperate and defect. In real-world prisoner's dilemmas, these choices are temporally extended and different strategies may correspond to sequences of actions, reflecting grades of cooperation. We introduce a Sequential Prisoner's Dilemma (SPD) game to better capture the aforementioned characteristics. In this work, we propose a deep multiagent reinforcement learning approach that investigates the evolution of mutual cooperation in SPD games. Our approa"},"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":"1803.00162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-01T01:53:52Z","cross_cats_sorted":["cs.GT","cs.LG","cs.MA"],"title_canon_sha256":"454f38c8cf7406c167648645f1def52c774c1fab3c61b613196c5daefef21880","abstract_canon_sha256":"c9a7ea695783b2d71f79eab1256936d5d077219788c5067bb160b0ec8bbcf820"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:13.148674Z","signature_b64":"fFUSjp+A2eK/iX3jRtYM7Zqp0Y6uACUn4Ze0Vg2KpOpb+JYUqN6+CmFTt5rtgl4mBXi54euIA9tPDIW5UBOQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"312ea559a662d95fa1cd22fc9e9d723482136cd14c3f9d6376ffe926ce90190f","last_reissued_at":"2026-05-18T00:22:13.148105Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:13.148105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Cooperation in Sequential Prisoner's Dilemmas: a Deep Multiagent Reinforcement Learning Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Jianye Hao, Matthew Taylor, Weixun Wang, Yixi Wang","submitted_at":"2018-03-01T01:53:52Z","abstract_excerpt":"The Iterated Prisoner's Dilemma has guided research on social dilemmas for decades. However, it distinguishes between only two atomic actions: cooperate and defect. In real-world prisoner's dilemmas, these choices are temporally extended and different strategies may correspond to sequences of actions, reflecting grades of cooperation. We introduce a Sequential Prisoner's Dilemma (SPD) game to better capture the aforementioned characteristics. In this work, we propose a deep multiagent reinforcement learning approach that investigates the evolution of mutual cooperation in SPD games. Our approa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00162","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":""},"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":"1803.00162","created_at":"2026-05-18T00:22:13.148175+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.00162v1","created_at":"2026-05-18T00:22:13.148175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00162","created_at":"2026-05-18T00:22:13.148175+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEXKKWNGMLMV","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEXKKWNGMLMV7ION","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEXKKWNG","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GEXKKWNGMLMV7IONEL6J5HLSGS","json":"https://pith.science/pith/GEXKKWNGMLMV7IONEL6J5HLSGS.json","graph_json":"https://pith.science/api/pith-number/GEXKKWNGMLMV7IONEL6J5HLSGS/graph.json","events_json":"https://pith.science/api/pith-number/GEXKKWNGMLMV7IONEL6J5HLSGS/events.json","paper":"https://pith.science/paper/GEXKKWNG"},"agent_actions":{"view_html":"https://pith.science/pith/GEXKKWNGMLMV7IONEL6J5HLSGS","download_json":"https://pith.science/pith/GEXKKWNGMLMV7IONEL6J5HLSGS.json","view_paper":"https://pith.science/paper/GEXKKWNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.00162&json=true","fetch_graph":"https://pith.science/api/pith-number/GEXKKWNGMLMV7IONEL6J5HLSGS/graph.json","fetch_events":"https://pith.science/api/pith-number/GEXKKWNGMLMV7IONEL6J5HLSGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEXKKWNGMLMV7IONEL6J5HLSGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEXKKWNGMLMV7IONEL6J5HLSGS/action/storage_attestation","attest_author":"https://pith.science/pith/GEXKKWNGMLMV7IONEL6J5HLSGS/action/author_attestation","sign_citation":"https://pith.science/pith/GEXKKWNGMLMV7IONEL6J5HLSGS/action/citation_signature","submit_replication":"https://pith.science/pith/GEXKKWNGMLMV7IONEL6J5HLSGS/action/replication_record"}},"created_at":"2026-05-18T00:22:13.148175+00:00","updated_at":"2026-05-18T00:22:13.148175+00:00"}