{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GU2NAXJR6ECTV53KOJ3ZMUNXYW","short_pith_number":"pith:GU2NAXJR","schema_version":"1.0","canonical_sha256":"3534d05d31f1053af76a72779651b7c59c1621deb188c5193a8531545b9f0344","source":{"kind":"arxiv","id":"2210.05492","version":1},"attestation_state":"computed","paper":{"title":"Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.GT","authors_text":"Adam Lerer, Alexander H Miller, Anton Bakhtin, Athul Paul Jacob, David J Wu, Gabriele Farina, Jonathan Gray, Noam Brown","submitted_at":"2022-10-11T14:47:35Z","abstract_excerpt":"No-press Diplomacy is a complex strategy game involving both cooperation and competition that has served as a benchmark for multi-agent AI research. While self-play reinforcement learning has resulted in numerous successes in purely adversarial games like chess, Go, and poker, self-play alone is insufficient for achieving optimal performance in domains involving cooperation with humans. We address this shortcoming by first introducing a planning algorithm we call DiL-piKL that regularizes a reward-maximizing policy toward a human imitation-learned policy. We prove that this is a no-regret lear"},"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":"2210.05492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-10-11T14:47:35Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"title_canon_sha256":"5c2167f5a089d5d2b81fdbde2b537968f6f09bf44de1b6579135bf49b3e1cdd3","abstract_canon_sha256":"954d96ae1552a5d73b60885552e2addd775f4b33756ebdb5ef300dc3c51e7482"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:17.211828Z","signature_b64":"28dUD2wwu6Z1UAvbl3fBqfHo4fOesbrXtsgbPMukw9CSldDWiq7PvvKUOl7b/+cajYCXjlZV0zx6OED3gnlOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3534d05d31f1053af76a72779651b7c59c1621deb188c5193a8531545b9f0344","last_reissued_at":"2026-07-05T05:05:17.211090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:17.211090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.GT","authors_text":"Adam Lerer, Alexander H Miller, Anton Bakhtin, Athul Paul Jacob, David J Wu, Gabriele Farina, Jonathan Gray, Noam Brown","submitted_at":"2022-10-11T14:47:35Z","abstract_excerpt":"No-press Diplomacy is a complex strategy game involving both cooperation and competition that has served as a benchmark for multi-agent AI research. While self-play reinforcement learning has resulted in numerous successes in purely adversarial games like chess, Go, and poker, self-play alone is insufficient for achieving optimal performance in domains involving cooperation with humans. We address this shortcoming by first introducing a planning algorithm we call DiL-piKL that regularizes a reward-maximizing policy toward a human imitation-learned policy. We prove that this is a no-regret lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05492","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/2210.05492/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":"2210.05492","created_at":"2026-07-05T05:05:17.211167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05492v1","created_at":"2026-07-05T05:05:17.211167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05492","created_at":"2026-07-05T05:05:17.211167+00:00"},{"alias_kind":"pith_short_12","alias_value":"GU2NAXJR6ECT","created_at":"2026-07-05T05:05:17.211167+00:00"},{"alias_kind":"pith_short_16","alias_value":"GU2NAXJR6ECTV53K","created_at":"2026-07-05T05:05:17.211167+00:00"},{"alias_kind":"pith_short_8","alias_value":"GU2NAXJR","created_at":"2026-07-05T05:05:17.211167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19370","citing_title":"Human-like autonomy emerges from self-play and a pinch of human data","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07996","citing_title":"Nash without Numbers: A Social Choice Approach to Mixed Equilibria in Context-Ordinal Games","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW","json":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW.json","graph_json":"https://pith.science/api/pith-number/GU2NAXJR6ECTV53KOJ3ZMUNXYW/graph.json","events_json":"https://pith.science/api/pith-number/GU2NAXJR6ECTV53KOJ3ZMUNXYW/events.json","paper":"https://pith.science/paper/GU2NAXJR"},"agent_actions":{"view_html":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW","download_json":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW.json","view_paper":"https://pith.science/paper/GU2NAXJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05492&json=true","fetch_graph":"https://pith.science/api/pith-number/GU2NAXJR6ECTV53KOJ3ZMUNXYW/graph.json","fetch_events":"https://pith.science/api/pith-number/GU2NAXJR6ECTV53KOJ3ZMUNXYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW/action/storage_attestation","attest_author":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW/action/author_attestation","sign_citation":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW/action/citation_signature","submit_replication":"https://pith.science/pith/GU2NAXJR6ECTV53KOJ3ZMUNXYW/action/replication_record"}},"created_at":"2026-07-05T05:05:17.211167+00:00","updated_at":"2026-07-05T05:05:17.211167+00:00"}