{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OOTT6AMMRPYJM4WYCNDN7QWH4Z","short_pith_number":"pith:OOTT6AMM","schema_version":"1.0","canonical_sha256":"73a73f018c8bf09672d81346dfc2c7e65b6f44631635915e0157bc2ba48a2255","source":{"kind":"arxiv","id":"2011.14267","version":1},"attestation_state":"computed","paper":{"title":"Minimax Sample Complexity for Turn-based Stochastic Game","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin F. Yang, Qiwen Cui","submitted_at":"2020-11-29T03:58:45Z","abstract_excerpt":"The empirical success of Multi-agent reinforcement learning is encouraging, while few theoretical guarantees have been revealed. In this work, we prove that the plug-in solver approach, probably the most natural reinforcement learning algorithm, achieves minimax sample complexity for turn-based stochastic game (TBSG). Specifically, we plan in an empirical TBSG by utilizing a `simulator' that allows sampling from arbitrary state-action pair. We show that the empirical Nash equilibrium strategy is an approximate Nash equilibrium strategy in the true TBSG and give both problem-dependent and probl"},"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":"2011.14267","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-29T03:58:45Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"aec6080925126aeccc2621c48534a9d6e13032de6d6c2ea995ad65a3592ec6d2","abstract_canon_sha256":"b370f17b007149a3cbeb2000e6b1fb1aaefde2559e9a05df36906c0ee8fa3056"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:55:19.103694Z","signature_b64":"QAmBQq/fOXOIIhCrtqVHxOQs6jcwqAVr4bUfevfdUMOKBkfEodPlElg8P8y+jaFVZf0s7B4tOE+qddv79KxqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73a73f018c8bf09672d81346dfc2c7e65b6f44631635915e0157bc2ba48a2255","last_reissued_at":"2026-07-05T01:55:19.103103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:55:19.103103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimax Sample Complexity for Turn-based Stochastic Game","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin F. Yang, Qiwen Cui","submitted_at":"2020-11-29T03:58:45Z","abstract_excerpt":"The empirical success of Multi-agent reinforcement learning is encouraging, while few theoretical guarantees have been revealed. In this work, we prove that the plug-in solver approach, probably the most natural reinforcement learning algorithm, achieves minimax sample complexity for turn-based stochastic game (TBSG). Specifically, we plan in an empirical TBSG by utilizing a `simulator' that allows sampling from arbitrary state-action pair. We show that the empirical Nash equilibrium strategy is an approximate Nash equilibrium strategy in the true TBSG and give both problem-dependent and probl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14267","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/2011.14267/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":"2011.14267","created_at":"2026-07-05T01:55:19.103167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.14267v1","created_at":"2026-07-05T01:55:19.103167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14267","created_at":"2026-07-05T01:55:19.103167+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOTT6AMMRPYJ","created_at":"2026-07-05T01:55:19.103167+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOTT6AMMRPYJM4WY","created_at":"2026-07-05T01:55:19.103167+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOTT6AMM","created_at":"2026-07-05T01:55:19.103167+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/OOTT6AMMRPYJM4WYCNDN7QWH4Z","json":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z.json","graph_json":"https://pith.science/api/pith-number/OOTT6AMMRPYJM4WYCNDN7QWH4Z/graph.json","events_json":"https://pith.science/api/pith-number/OOTT6AMMRPYJM4WYCNDN7QWH4Z/events.json","paper":"https://pith.science/paper/OOTT6AMM"},"agent_actions":{"view_html":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z","download_json":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z.json","view_paper":"https://pith.science/paper/OOTT6AMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.14267&json=true","fetch_graph":"https://pith.science/api/pith-number/OOTT6AMMRPYJM4WYCNDN7QWH4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/OOTT6AMMRPYJM4WYCNDN7QWH4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z/action/storage_attestation","attest_author":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z/action/author_attestation","sign_citation":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z/action/citation_signature","submit_replication":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z/action/replication_record"}},"created_at":"2026-07-05T01:55:19.103167+00:00","updated_at":"2026-07-05T01:55:19.103167+00:00"}