{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WMEO4RFIDR6DSL7T2O3M3Z7SXI","short_pith_number":"pith:WMEO4RFI","schema_version":"1.0","canonical_sha256":"b308ee44a81c7c392ff3d3b6cde7f2ba333f3059fd0fadb14e4cc9c694906ad0","source":{"kind":"arxiv","id":"2303.04096","version":1},"attestation_state":"computed","paper":{"title":"Mastering Strategy Card Game (Legends of Code and Magic) via End-to-End Policy and Optimistic Smooth Fictitious Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.LG","authors_text":"Changnan Xiao, Haowei Liang, Jie Chen, Peng Sun, Shihong Deng, Wei Xi, Xuefeng Huang, Yongxin Zhang","submitted_at":"2023-03-07T17:55:28Z","abstract_excerpt":"Deep Reinforcement Learning combined with Fictitious Play shows impressive results on many benchmark games, most of which are, however, single-stage. In contrast, real-world decision making problems may consist of multiple stages, where the observation spaces and the action spaces can be completely different across stages. We study a two-stage strategy card game Legends of Code and Magic and propose an end-to-end policy to address the difficulties that arise in multi-stage game. We also propose an optimistic smooth fictitious play algorithm to find the Nash Equilibrium for the two-player game."},"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":"2303.04096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-07T17:55:28Z","cross_cats_sorted":["cs.AI","cs.GT"],"title_canon_sha256":"7688ff09329f326663beb1afeadb2de6598c8ddfdf827733f31a76b4ff094db0","abstract_canon_sha256":"652c20c2d34db158aef4b8a726bb54eee7884284e9fed042712a9b6e609a3ffa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:03.233748Z","signature_b64":"uvVLvY7x+q4+pjcA/xlWPUNkMZVv6jFkRP1/fVvsG9pge4K8oZvM66WHQmzOB2IC26N6cwq/4k4xi26ORysnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b308ee44a81c7c392ff3d3b6cde7f2ba333f3059fd0fadb14e4cc9c694906ad0","last_reissued_at":"2026-07-05T05:49:03.233203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:03.233203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mastering Strategy Card Game (Legends of Code and Magic) via End-to-End Policy and Optimistic Smooth Fictitious Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.LG","authors_text":"Changnan Xiao, Haowei Liang, Jie Chen, Peng Sun, Shihong Deng, Wei Xi, Xuefeng Huang, Yongxin Zhang","submitted_at":"2023-03-07T17:55:28Z","abstract_excerpt":"Deep Reinforcement Learning combined with Fictitious Play shows impressive results on many benchmark games, most of which are, however, single-stage. In contrast, real-world decision making problems may consist of multiple stages, where the observation spaces and the action spaces can be completely different across stages. We study a two-stage strategy card game Legends of Code and Magic and propose an end-to-end policy to address the difficulties that arise in multi-stage game. We also propose an optimistic smooth fictitious play algorithm to find the Nash Equilibrium for the two-player game."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04096","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/2303.04096/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":"2303.04096","created_at":"2026-07-05T05:49:03.233266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.04096v1","created_at":"2026-07-05T05:49:03.233266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04096","created_at":"2026-07-05T05:49:03.233266+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMEO4RFIDR6D","created_at":"2026-07-05T05:49:03.233266+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMEO4RFIDR6DSL7T","created_at":"2026-07-05T05:49:03.233266+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMEO4RFI","created_at":"2026-07-05T05:49:03.233266+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/WMEO4RFIDR6DSL7T2O3M3Z7SXI","json":"https://pith.science/pith/WMEO4RFIDR6DSL7T2O3M3Z7SXI.json","graph_json":"https://pith.science/api/pith-number/WMEO4RFIDR6DSL7T2O3M3Z7SXI/graph.json","events_json":"https://pith.science/api/pith-number/WMEO4RFIDR6DSL7T2O3M3Z7SXI/events.json","paper":"https://pith.science/paper/WMEO4RFI"},"agent_actions":{"view_html":"https://pith.science/pith/WMEO4RFIDR6DSL7T2O3M3Z7SXI","download_json":"https://pith.science/pith/WMEO4RFIDR6DSL7T2O3M3Z7SXI.json","view_paper":"https://pith.science/paper/WMEO4RFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.04096&json=true","fetch_graph":"https://pith.science/api/pith-number/WMEO4RFIDR6DSL7T2O3M3Z7SXI/graph.json","fetch_events":"https://pith.science/api/pith-number/WMEO4RFIDR6DSL7T2O3M3Z7SXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMEO4RFIDR6DSL7T2O3M3Z7SXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMEO4RFIDR6DSL7T2O3M3Z7SXI/action/storage_attestation","attest_author":"https://pith.science/pith/WMEO4RFIDR6DSL7T2O3M3Z7SXI/action/author_attestation","sign_citation":"https://pith.science/pith/WMEO4RFIDR6DSL7T2O3M3Z7SXI/action/citation_signature","submit_replication":"https://pith.science/pith/WMEO4RFIDR6DSL7T2O3M3Z7SXI/action/replication_record"}},"created_at":"2026-07-05T05:49:03.233266+00:00","updated_at":"2026-07-05T05:49:03.233266+00:00"}