{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TUCT2YAZJS3FMJTIFYWZ35CDQ3","short_pith_number":"pith:TUCT2YAZ","schema_version":"1.0","canonical_sha256":"9d053d60194cb65626682e2d9df44386d63025728722ef891c4590fe71d9993f","source":{"kind":"arxiv","id":"1808.10442","version":1},"attestation_state":"computed","paper":{"title":"Application of Self-Play Reinforcement Learning to a Four-Player Game of Imperfect Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Henry Charlesworth","submitted_at":"2018-08-30T11:26:59Z","abstract_excerpt":"We introduce a new virtual environment for simulating a card game known as \"Big 2\". This is a four-player game of imperfect information with a relatively complicated action space (being allowed to play 1,2,3,4 or 5 card combinations from an initial starting hand of 13 cards). As such it poses a challenge for many current reinforcement learning methods. We then use the recently proposed \"Proximal Policy Optimization\" algorithm to train a deep neural network to play the game, purely learning via self-play, and find that it is able to reach a level which outperforms amateur human players after on"},"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":"1808.10442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-30T11:26:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2ef0fe1be1709e8897a91009e52d26760ce6ba5251c32cd8605c006d62cb3940","abstract_canon_sha256":"6c88d29881c34282bab7d30b84d3da469ac20d01e4665f7f225784778e15966f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:45.631343Z","signature_b64":"mIHX+M2NE+qyqMRVmOaQZU5kOAKlDKcRGdHbwp8WZI8qlbsJ6PeahuyKiTrP3GWWWoWjsKXwoL9e6GVVHeD4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d053d60194cb65626682e2d9df44386d63025728722ef891c4590fe71d9993f","last_reissued_at":"2026-05-18T00:06:45.630827Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:45.630827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Application of Self-Play Reinforcement Learning to a Four-Player Game of Imperfect Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Henry Charlesworth","submitted_at":"2018-08-30T11:26:59Z","abstract_excerpt":"We introduce a new virtual environment for simulating a card game known as \"Big 2\". This is a four-player game of imperfect information with a relatively complicated action space (being allowed to play 1,2,3,4 or 5 card combinations from an initial starting hand of 13 cards). As such it poses a challenge for many current reinforcement learning methods. We then use the recently proposed \"Proximal Policy Optimization\" algorithm to train a deep neural network to play the game, purely learning via self-play, and find that it is able to reach a level which outperforms amateur human players after on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10442","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":"1808.10442","created_at":"2026-05-18T00:06:45.630911+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.10442v1","created_at":"2026-05-18T00:06:45.630911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10442","created_at":"2026-05-18T00:06:45.630911+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUCT2YAZJS3F","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUCT2YAZJS3FMJTI","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUCT2YAZ","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.28863","citing_title":"Self-Play Reinforcement Learning under Imperfect Information in Big 2","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3","json":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3.json","graph_json":"https://pith.science/api/pith-number/TUCT2YAZJS3FMJTIFYWZ35CDQ3/graph.json","events_json":"https://pith.science/api/pith-number/TUCT2YAZJS3FMJTIFYWZ35CDQ3/events.json","paper":"https://pith.science/paper/TUCT2YAZ"},"agent_actions":{"view_html":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3","download_json":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3.json","view_paper":"https://pith.science/paper/TUCT2YAZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.10442&json=true","fetch_graph":"https://pith.science/api/pith-number/TUCT2YAZJS3FMJTIFYWZ35CDQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/TUCT2YAZJS3FMJTIFYWZ35CDQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3/action/storage_attestation","attest_author":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3/action/author_attestation","sign_citation":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3/action/citation_signature","submit_replication":"https://pith.science/pith/TUCT2YAZJS3FMJTIFYWZ35CDQ3/action/replication_record"}},"created_at":"2026-05-18T00:06:45.630911+00:00","updated_at":"2026-05-18T00:06:45.630911+00:00"}