{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M4NAEV5OKKVDDB4Z3U6JZLPH27","short_pith_number":"pith:M4NAEV5O","schema_version":"1.0","canonical_sha256":"671a0257ae52aa318799dd3c9cade7d7ea0fb88ceb7ee6f6f37a6a4f2226c584","source":{"kind":"arxiv","id":"2605.28863","version":1},"attestation_state":"computed","paper":{"title":"Self-Play Reinforcement Learning under Imperfect Information in Big 2","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aalok Patwa","submitted_at":"2026-05-21T21:56:09Z","abstract_excerpt":"Imperfect-information multiplayer games test whether agents can act under hidden information, sparse rewards, and non-stationary opponents. We study these challenges in Big 2, a four-player imperfect-information card game. We develop a self-play RL framework for Big 2 that enables controlled comparisons between policy-gradient and value-approximating agents. Under a common environment, input representation, training budget, and evaluation protocol, PPO outperforms Monte Carlo Q approximation, SARSA, and Q-learning against random, greedy, and heuristic Big 2 opponents. We further find that mode"},"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":"2605.28863","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T21:56:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3391501e007ae9f66f7dec54814b8dca98afa14c061b8841159b260a4d648e4e","abstract_canon_sha256":"553b7c5fbb36113dd893986b1e8e909eade5b4f0abbe5b81f563f1ce5b0c4483"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T00:04:14.627909Z","signature_b64":"BqDUS18ZDgOT2Nb4cRsizWfIyImSLhcRRbTqZtwZtwIvg8ltg+RmG0eC3C566SGx9kTkUAnWsDnVWzXKhbPUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"671a0257ae52aa318799dd3c9cade7d7ea0fb88ceb7ee6f6f37a6a4f2226c584","last_reissued_at":"2026-05-29T00:04:14.627489Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T00:04:14.627489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Play Reinforcement Learning under Imperfect Information in Big 2","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aalok Patwa","submitted_at":"2026-05-21T21:56:09Z","abstract_excerpt":"Imperfect-information multiplayer games test whether agents can act under hidden information, sparse rewards, and non-stationary opponents. We study these challenges in Big 2, a four-player imperfect-information card game. We develop a self-play RL framework for Big 2 that enables controlled comparisons between policy-gradient and value-approximating agents. Under a common environment, input representation, training budget, and evaluation protocol, PPO outperforms Monte Carlo Q approximation, SARSA, and Q-learning against random, greedy, and heuristic Big 2 opponents. We further find that mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28863","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/2605.28863/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":"2605.28863","created_at":"2026-05-29T00:04:14.627548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28863v1","created_at":"2026-05-29T00:04:14.627548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28863","created_at":"2026-05-29T00:04:14.627548+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4NAEV5OKKVD","created_at":"2026-05-29T00:04:14.627548+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4NAEV5OKKVDDB4Z","created_at":"2026-05-29T00:04:14.627548+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4NAEV5O","created_at":"2026-05-29T00:04:14.627548+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/M4NAEV5OKKVDDB4Z3U6JZLPH27","json":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27.json","graph_json":"https://pith.science/api/pith-number/M4NAEV5OKKVDDB4Z3U6JZLPH27/graph.json","events_json":"https://pith.science/api/pith-number/M4NAEV5OKKVDDB4Z3U6JZLPH27/events.json","paper":"https://pith.science/paper/M4NAEV5O"},"agent_actions":{"view_html":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27","download_json":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27.json","view_paper":"https://pith.science/paper/M4NAEV5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28863&json=true","fetch_graph":"https://pith.science/api/pith-number/M4NAEV5OKKVDDB4Z3U6JZLPH27/graph.json","fetch_events":"https://pith.science/api/pith-number/M4NAEV5OKKVDDB4Z3U6JZLPH27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27/action/storage_attestation","attest_author":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27/action/author_attestation","sign_citation":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27/action/citation_signature","submit_replication":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27/action/replication_record"}},"created_at":"2026-05-29T00:04:14.627548+00:00","updated_at":"2026-05-29T00:04:14.627548+00:00"}