{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2DUADVJCHT5OWBZTCLQB4M4IT7","short_pith_number":"pith:2DUADVJC","schema_version":"1.0","canonical_sha256":"d0e801d5223cfaeb073312e01e33889fe845b10f017c2d4ddcbdf721a85f9891","source":{"kind":"arxiv","id":"2504.04783","version":1},"attestation_state":"computed","paper":{"title":"Playing Non-Embedded Card-Based Games with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lipeng Wan, Qiang Wan, Tianyang Wu, Xuguang Lan, Yuhang Wang","submitted_at":"2025-04-07T07:26:02Z","abstract_excerpt":"Significant progress has been made in AI for games, including board games, MOBA, and RTS games. However, complex agents are typically developed in an embedded manner, directly accessing game state information, unlike human players who rely on noisy visual data, leading to unfair competition. Developing complex non-embedded agents remains challenging, especially in card-based RTS games with complex features and large state spaces. We propose a non-embedded offline reinforcement learning training strategy using visual inputs to achieve real-time autonomous gameplay in the RTS game Clash Royale. "},"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":"2504.04783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-07T07:26:02Z","cross_cats_sorted":[],"title_canon_sha256":"93b7961c67ab3a0b0f3f1735576ae3c7350fd9391fe09e4a3b72d58d5a15d08e","abstract_canon_sha256":"93b27a9fbe9d6fb9cbd2616dcac99b4245e3f4dbec5f5f012176b5e3158c5797"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:29.625180Z","signature_b64":"PZT/cYpj8B5zkyEkl6N6rot3PP9/zYZgNe0Os4PJMVaWq3WHQ70E6LkLl71CAv06bdoEBXX9+6YYr9EhlVViBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0e801d5223cfaeb073312e01e33889fe845b10f017c2d4ddcbdf721a85f9891","last_reissued_at":"2026-07-05T10:45:29.624803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:29.624803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Playing Non-Embedded Card-Based Games with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lipeng Wan, Qiang Wan, Tianyang Wu, Xuguang Lan, Yuhang Wang","submitted_at":"2025-04-07T07:26:02Z","abstract_excerpt":"Significant progress has been made in AI for games, including board games, MOBA, and RTS games. However, complex agents are typically developed in an embedded manner, directly accessing game state information, unlike human players who rely on noisy visual data, leading to unfair competition. Developing complex non-embedded agents remains challenging, especially in card-based RTS games with complex features and large state spaces. We propose a non-embedded offline reinforcement learning training strategy using visual inputs to achieve real-time autonomous gameplay in the RTS game Clash Royale. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04783","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/2504.04783/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":"2504.04783","created_at":"2026-07-05T10:45:29.624857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04783v1","created_at":"2026-07-05T10:45:29.624857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04783","created_at":"2026-07-05T10:45:29.624857+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DUADVJCHT5O","created_at":"2026-07-05T10:45:29.624857+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DUADVJCHT5OWBZT","created_at":"2026-07-05T10:45:29.624857+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DUADVJC","created_at":"2026-07-05T10:45:29.624857+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/2DUADVJCHT5OWBZTCLQB4M4IT7","json":"https://pith.science/pith/2DUADVJCHT5OWBZTCLQB4M4IT7.json","graph_json":"https://pith.science/api/pith-number/2DUADVJCHT5OWBZTCLQB4M4IT7/graph.json","events_json":"https://pith.science/api/pith-number/2DUADVJCHT5OWBZTCLQB4M4IT7/events.json","paper":"https://pith.science/paper/2DUADVJC"},"agent_actions":{"view_html":"https://pith.science/pith/2DUADVJCHT5OWBZTCLQB4M4IT7","download_json":"https://pith.science/pith/2DUADVJCHT5OWBZTCLQB4M4IT7.json","view_paper":"https://pith.science/paper/2DUADVJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04783&json=true","fetch_graph":"https://pith.science/api/pith-number/2DUADVJCHT5OWBZTCLQB4M4IT7/graph.json","fetch_events":"https://pith.science/api/pith-number/2DUADVJCHT5OWBZTCLQB4M4IT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DUADVJCHT5OWBZTCLQB4M4IT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DUADVJCHT5OWBZTCLQB4M4IT7/action/storage_attestation","attest_author":"https://pith.science/pith/2DUADVJCHT5OWBZTCLQB4M4IT7/action/author_attestation","sign_citation":"https://pith.science/pith/2DUADVJCHT5OWBZTCLQB4M4IT7/action/citation_signature","submit_replication":"https://pith.science/pith/2DUADVJCHT5OWBZTCLQB4M4IT7/action/replication_record"}},"created_at":"2026-07-05T10:45:29.624857+00:00","updated_at":"2026-07-05T10:45:29.624857+00:00"}