{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:OOTT6AMMRPYJM4WYCNDN7QWH4Z","short_pith_number":"pith:OOTT6AMM","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"},"canonical_sha256":"73a73f018c8bf09672d81346dfc2c7e65b6f44631635915e0157bc2ba48a2255","source":{"kind":"arxiv","id":"2011.14267","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.14267","created_at":"2026-07-05T01:55:19Z"},{"alias_kind":"arxiv_version","alias_value":"2011.14267v1","created_at":"2026-07-05T01:55:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14267","created_at":"2026-07-05T01:55:19Z"},{"alias_kind":"pith_short_12","alias_value":"OOTT6AMMRPYJ","created_at":"2026-07-05T01:55:19Z"},{"alias_kind":"pith_short_16","alias_value":"OOTT6AMMRPYJM4WY","created_at":"2026-07-05T01:55:19Z"},{"alias_kind":"pith_short_8","alias_value":"OOTT6AMM","created_at":"2026-07-05T01:55:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:OOTT6AMMRPYJM4WYCNDN7QWH4Z","target":"record","payload":{"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"},"canonical_sha256":"73a73f018c8bf09672d81346dfc2c7e65b6f44631635915e0157bc2ba48a2255","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"},"source_kind":"arxiv","source_id":"2011.14267","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:55:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MVCYMuPKhDyBQhtR+lrDcygzc4rhRQSb2rqu3L6eeDimpeHo4WPRUeFsaSZtsIc55LR8EdE0rfQOo4ztspR4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T08:55:06.457095Z"},"content_sha256":"47676e686328f549125ecea7b02323874353f0818b1a4da6b4955808f5be746e","schema_version":"1.0","event_id":"sha256:47676e686328f549125ecea7b02323874353f0818b1a4da6b4955808f5be746e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:OOTT6AMMRPYJM4WYCNDN7QWH4Z","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:55:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7hM8AjZvEGo/MOK5rLWRCvbyujFZvbel5IPufDWATGPCvH2avqz7BGxv/UIWcmrJuWztNtBUSjXvVoK5P7tGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T08:55:06.457496Z"},"content_sha256":"ac222c44acfbec7e3ca65635cf9a14b8c177a979d374f90683cbfbfb9a36e126","schema_version":"1.0","event_id":"sha256:ac222c44acfbec7e3ca65635cf9a14b8c177a979d374f90683cbfbfb9a36e126"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z/bundle.json","state_url":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-13T08:55:06Z","links":{"resolver":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z","bundle":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z/bundle.json","state":"https://pith.science/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOTT6AMMRPYJM4WYCNDN7QWH4Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OOTT6AMMRPYJM4WYCNDN7QWH4Z","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b370f17b007149a3cbeb2000e6b1fb1aaefde2559e9a05df36906c0ee8fa3056","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-29T03:58:45Z","title_canon_sha256":"aec6080925126aeccc2621c48534a9d6e13032de6d6c2ea995ad65a3592ec6d2"},"schema_version":"1.0","source":{"id":"2011.14267","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.14267","created_at":"2026-07-05T01:55:19Z"},{"alias_kind":"arxiv_version","alias_value":"2011.14267v1","created_at":"2026-07-05T01:55:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14267","created_at":"2026-07-05T01:55:19Z"},{"alias_kind":"pith_short_12","alias_value":"OOTT6AMMRPYJ","created_at":"2026-07-05T01:55:19Z"},{"alias_kind":"pith_short_16","alias_value":"OOTT6AMMRPYJM4WY","created_at":"2026-07-05T01:55:19Z"},{"alias_kind":"pith_short_8","alias_value":"OOTT6AMM","created_at":"2026-07-05T01:55:19Z"}],"graph_snapshots":[{"event_id":"sha256:ac222c44acfbec7e3ca65635cf9a14b8c177a979d374f90683cbfbfb9a36e126","target":"graph","created_at":"2026-07-05T01:55:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.14267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lin F. Yang, Qiwen Cui","cross_cats":["cs.GT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-29T03:58:45Z","title":"Minimax Sample Complexity for Turn-based Stochastic Game"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14267","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:47676e686328f549125ecea7b02323874353f0818b1a4da6b4955808f5be746e","target":"record","created_at":"2026-07-05T01:55:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b370f17b007149a3cbeb2000e6b1fb1aaefde2559e9a05df36906c0ee8fa3056","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-29T03:58:45Z","title_canon_sha256":"aec6080925126aeccc2621c48534a9d6e13032de6d6c2ea995ad65a3592ec6d2"},"schema_version":"1.0","source":{"id":"2011.14267","kind":"arxiv","version":1}},"canonical_sha256":"73a73f018c8bf09672d81346dfc2c7e65b6f44631635915e0157bc2ba48a2255","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73a73f018c8bf09672d81346dfc2c7e65b6f44631635915e0157bc2ba48a2255","first_computed_at":"2026-07-05T01:55:19.103103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:55:19.103103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QAmBQq/fOXOIIhCrtqVHxOQs6jcwqAVr4bUfevfdUMOKBkfEodPlElg8P8y+jaFVZf0s7B4tOE+qddv79KxqCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:55:19.103694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.14267","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47676e686328f549125ecea7b02323874353f0818b1a4da6b4955808f5be746e","sha256:ac222c44acfbec7e3ca65635cf9a14b8c177a979d374f90683cbfbfb9a36e126"],"state_sha256":"8dc54cbf55a99715e0a8c60ff92e077de9d24d28d0e3807b772303d24d23f70f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R8rcREC37TToonzHVluBhzyXrr4Lu/xabUeCjnXUy0bY7Yia8mfWMQNthJ2b7plSSyNdymSIs4iaBgAq9rrIDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T08:55:06.462024Z","bundle_sha256":"ecac0eb2c78f0227f575c4147bb59a1430dd55df09839ceea46523a12dd760f7"}}