{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:737QV3ULMFNXS3TP4ED6DJWQ7P","short_pith_number":"pith:737QV3UL","canonical_record":{"source":{"id":"1906.00423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-02T15:24:19Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"54d16dec537c9396bafbeb37793e268ae539c0a97a7d42ed37b996cdea1c6432","abstract_canon_sha256":"9edc14726a7891e489b235bce79a511d1cbf03fbf755d75bcb7129b45d95d34e"},"schema_version":"1.0"},"canonical_sha256":"feff0aee8b615b796e6fe107e1a6d0fbd235ca9d735182407ce1573c825c7e51","source":{"kind":"arxiv","id":"1906.00423","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00423","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00423v1","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00423","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"737QV3ULMFNX","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"737QV3ULMFNXS3TP","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"737QV3UL","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:737QV3ULMFNXS3TP4ED6DJWQ7P","target":"record","payload":{"canonical_record":{"source":{"id":"1906.00423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-02T15:24:19Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"54d16dec537c9396bafbeb37793e268ae539c0a97a7d42ed37b996cdea1c6432","abstract_canon_sha256":"9edc14726a7891e489b235bce79a511d1cbf03fbf755d75bcb7129b45d95d34e"},"schema_version":"1.0"},"canonical_sha256":"feff0aee8b615b796e6fe107e1a6d0fbd235ca9d735182407ce1573c825c7e51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:27.131444Z","signature_b64":"RODdLjxeI/HnY6PbSdvo7hu8m1hlHluJIZKW+hfc0gPOAsnB2ZPyvcN7IyfnY8tTy14OKlN/x+sHZ2cJVM9YAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"feff0aee8b615b796e6fe107e1a6d0fbd235ca9d735182407ce1573c825c7e51","last_reissued_at":"2026-05-17T23:44:27.130947Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:27.130947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.00423","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":"2026-05-17T23:44:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"reBWLR6Go/LhWJL+Qc+gU/vTM+1sPUsi55mREg1gkxf7PMVsuGwTt2dncBKBrrG3zXsa3WZjoRdoSgW8jtcZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T21:37:06.799405Z"},"content_sha256":"8b5e92d790348d3407e9f38dec74001e41c1641c0b8a2451724cf22e567167a3","schema_version":"1.0","event_id":"sha256:8b5e92d790348d3407e9f38dec74001e41c1641c0b8a2451724cf22e567167a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:737QV3ULMFNXS3TP4ED6DJWQ7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Feature-Based Q-Learning for Two-Player Stochastic Games","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, Mengdi Wang, Zeyu Jia","submitted_at":"2019-06-02T15:24:19Z","abstract_excerpt":"Consider a two-player zero-sum stochastic game where the transition function can be embedded in a given feature space. We propose a two-player Q-learning algorithm for approximating the Nash equilibrium strategy via sampling. The algorithm is shown to find an $\\epsilon$-optimal strategy using sample size linear to the number of features. To further improve its sample efficiency, we develop an accelerated algorithm by adopting techniques such as variance reduction, monotonicity preservation and two-sided strategy approximation. We prove that the algorithm is guaranteed to find an $\\epsilon$-opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00423","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":""},"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":"2026-05-17T23:44:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hky2X8nbgxHByo2FFVV1QtnOM5ITrC1Km+LYQwCXp0TPnueKREnQE8sxDTD9wq1LIX/wyp9fCWWmVFB3TFoqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T21:37:06.799878Z"},"content_sha256":"9959ea4de22f883358852c84c89e438425f1343cf391890a63129840f508f7d5","schema_version":"1.0","event_id":"sha256:9959ea4de22f883358852c84c89e438425f1343cf391890a63129840f508f7d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/737QV3ULMFNXS3TP4ED6DJWQ7P/bundle.json","state_url":"https://pith.science/pith/737QV3ULMFNXS3TP4ED6DJWQ7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/737QV3ULMFNXS3TP4ED6DJWQ7P/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":"2026-05-30T21:37:06Z","links":{"resolver":"https://pith.science/pith/737QV3ULMFNXS3TP4ED6DJWQ7P","bundle":"https://pith.science/pith/737QV3ULMFNXS3TP4ED6DJWQ7P/bundle.json","state":"https://pith.science/pith/737QV3ULMFNXS3TP4ED6DJWQ7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/737QV3ULMFNXS3TP4ED6DJWQ7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:737QV3ULMFNXS3TP4ED6DJWQ7P","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":"9edc14726a7891e489b235bce79a511d1cbf03fbf755d75bcb7129b45d95d34e","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-02T15:24:19Z","title_canon_sha256":"54d16dec537c9396bafbeb37793e268ae539c0a97a7d42ed37b996cdea1c6432"},"schema_version":"1.0","source":{"id":"1906.00423","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00423","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00423v1","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00423","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"737QV3ULMFNX","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"737QV3ULMFNXS3TP","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"737QV3UL","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:9959ea4de22f883358852c84c89e438425f1343cf391890a63129840f508f7d5","target":"graph","created_at":"2026-05-17T23:44:27Z","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"},"paper":{"abstract_excerpt":"Consider a two-player zero-sum stochastic game where the transition function can be embedded in a given feature space. We propose a two-player Q-learning algorithm for approximating the Nash equilibrium strategy via sampling. The algorithm is shown to find an $\\epsilon$-optimal strategy using sample size linear to the number of features. To further improve its sample efficiency, we develop an accelerated algorithm by adopting techniques such as variance reduction, monotonicity preservation and two-sided strategy approximation. We prove that the algorithm is guaranteed to find an $\\epsilon$-opt","authors_text":"Lin F. Yang, Mengdi Wang, Zeyu Jia","cross_cats":["cs.GT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-02T15:24:19Z","title":"Feature-Based Q-Learning for Two-Player Stochastic Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00423","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":"sha256:8b5e92d790348d3407e9f38dec74001e41c1641c0b8a2451724cf22e567167a3","target":"record","created_at":"2026-05-17T23:44:27Z","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":"9edc14726a7891e489b235bce79a511d1cbf03fbf755d75bcb7129b45d95d34e","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-02T15:24:19Z","title_canon_sha256":"54d16dec537c9396bafbeb37793e268ae539c0a97a7d42ed37b996cdea1c6432"},"schema_version":"1.0","source":{"id":"1906.00423","kind":"arxiv","version":1}},"canonical_sha256":"feff0aee8b615b796e6fe107e1a6d0fbd235ca9d735182407ce1573c825c7e51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"feff0aee8b615b796e6fe107e1a6d0fbd235ca9d735182407ce1573c825c7e51","first_computed_at":"2026-05-17T23:44:27.130947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:27.130947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RODdLjxeI/HnY6PbSdvo7hu8m1hlHluJIZKW+hfc0gPOAsnB2ZPyvcN7IyfnY8tTy14OKlN/x+sHZ2cJVM9YAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:27.131444Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.00423","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b5e92d790348d3407e9f38dec74001e41c1641c0b8a2451724cf22e567167a3","sha256:9959ea4de22f883358852c84c89e438425f1343cf391890a63129840f508f7d5"],"state_sha256":"bf85efc542f8841dc5bcf69c761d191a43cc805b150fcd56401a8c43bf19ac4c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HckfeiOJXe0+8MUl/bQk7ImREhx+riTN1Z7hf4BMchpxuDHmaSfsronAiKrHHGi/q3+kdI9m0CD0cpsk2x/VAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T21:37:06.802344Z","bundle_sha256":"7f2fa081c509b59f201e452079c73101aa80c403ef4a400a6d83b729a9e910e7"}}