{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:67A5KBTOSNJF6CEUNIYSTCFTMB","short_pith_number":"pith:67A5KBTO","schema_version":"1.0","canonical_sha256":"f7c1d5066e93525f08946a312988b3606d4c3dbac9f7e669aceef7a580c9bde0","source":{"kind":"arxiv","id":"2006.04635","version":4},"attestation_state":"computed","paper":{"title":"Learning to Play No-Press Diplomacy with Best Response Policy Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Tacchetti, Ian Gemp, J\\'anos Kram\\'ar, Julien P\\'erolat, Marc Lanctot, Nicolas Porcel, Richard Everett, Roman Werpachowski, Satinder Singh, Thomas Anthony, Thomas C. Hudson, Thore Graepel, Tom Eccles, Yoram Bachrach","submitted_at":"2020-06-08T14:33:31Z","abstract_excerpt":"Recent advances in deep reinforcement learning (RL) have led to considerable progress in many 2-player zero-sum games, such as Go, Poker and Starcraft. The purely adversarial nature of such games allows for conceptually simple and principled application of RL methods. However real-world settings are many-agent, and agent interactions are complex mixtures of common-interest and competitive aspects. We consider Diplomacy, a 7-player board game designed to accentuate dilemmas resulting from many-agent interactions. It also features a large combinatorial action space and simultaneous moves, which "},"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":"2006.04635","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T14:33:31Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"title_canon_sha256":"64900ef4b49bcda177fc7fa8a476933c183453ee42291735147b83c08ba356f5","abstract_canon_sha256":"b89e30226e41962194fb35943df289d47a0586c8f6d38ea91979a50d6d54aee2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:45:07.623159Z","signature_b64":"2EXZNro9Rayy1LOWnDWyoPI+zU0/0UReksBRRd58RvmVnpkssOxVVphVeXAfeqrwQfWEoCGZiJwfFI9bRppwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7c1d5066e93525f08946a312988b3606d4c3dbac9f7e669aceef7a580c9bde0","last_reissued_at":"2026-07-05T03:45:07.622657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:45:07.622657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Play No-Press Diplomacy with Best Response Policy Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Tacchetti, Ian Gemp, J\\'anos Kram\\'ar, Julien P\\'erolat, Marc Lanctot, Nicolas Porcel, Richard Everett, Roman Werpachowski, Satinder Singh, Thomas Anthony, Thomas C. Hudson, Thore Graepel, Tom Eccles, Yoram Bachrach","submitted_at":"2020-06-08T14:33:31Z","abstract_excerpt":"Recent advances in deep reinforcement learning (RL) have led to considerable progress in many 2-player zero-sum games, such as Go, Poker and Starcraft. The purely adversarial nature of such games allows for conceptually simple and principled application of RL methods. However real-world settings are many-agent, and agent interactions are complex mixtures of common-interest and competitive aspects. We consider Diplomacy, a 7-player board game designed to accentuate dilemmas resulting from many-agent interactions. It also features a large combinatorial action space and simultaneous moves, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04635","kind":"arxiv","version":4},"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/2006.04635/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":"2006.04635","created_at":"2026-07-05T03:45:07.622718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04635v4","created_at":"2026-07-05T03:45:07.622718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04635","created_at":"2026-07-05T03:45:07.622718+00:00"},{"alias_kind":"pith_short_12","alias_value":"67A5KBTOSNJF","created_at":"2026-07-05T03:45:07.622718+00:00"},{"alias_kind":"pith_short_16","alias_value":"67A5KBTOSNJF6CEU","created_at":"2026-07-05T03:45:07.622718+00:00"},{"alias_kind":"pith_short_8","alias_value":"67A5KBTO","created_at":"2026-07-05T03:45:07.622718+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/67A5KBTOSNJF6CEUNIYSTCFTMB","json":"https://pith.science/pith/67A5KBTOSNJF6CEUNIYSTCFTMB.json","graph_json":"https://pith.science/api/pith-number/67A5KBTOSNJF6CEUNIYSTCFTMB/graph.json","events_json":"https://pith.science/api/pith-number/67A5KBTOSNJF6CEUNIYSTCFTMB/events.json","paper":"https://pith.science/paper/67A5KBTO"},"agent_actions":{"view_html":"https://pith.science/pith/67A5KBTOSNJF6CEUNIYSTCFTMB","download_json":"https://pith.science/pith/67A5KBTOSNJF6CEUNIYSTCFTMB.json","view_paper":"https://pith.science/paper/67A5KBTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04635&json=true","fetch_graph":"https://pith.science/api/pith-number/67A5KBTOSNJF6CEUNIYSTCFTMB/graph.json","fetch_events":"https://pith.science/api/pith-number/67A5KBTOSNJF6CEUNIYSTCFTMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67A5KBTOSNJF6CEUNIYSTCFTMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67A5KBTOSNJF6CEUNIYSTCFTMB/action/storage_attestation","attest_author":"https://pith.science/pith/67A5KBTOSNJF6CEUNIYSTCFTMB/action/author_attestation","sign_citation":"https://pith.science/pith/67A5KBTOSNJF6CEUNIYSTCFTMB/action/citation_signature","submit_replication":"https://pith.science/pith/67A5KBTOSNJF6CEUNIYSTCFTMB/action/replication_record"}},"created_at":"2026-07-05T03:45:07.622718+00:00","updated_at":"2026-07-05T03:45:07.622718+00:00"}