{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:O7VLW5QUUOHJDCLPUN23V7E2EW","short_pith_number":"pith:O7VLW5QU","canonical_record":{"source":{"id":"1109.1528","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2011-09-07T18:21:39Z","cross_cats_sorted":["cs.LG","cs.MA","nlin.AO","q-bio.PE"],"title_canon_sha256":"4eb355370797259484bd28214858619baf00cfb5fa529ece708e1e34cf0247e8","abstract_canon_sha256":"7ce20b666ee5f4f448bba1943920950e98d676aed1c678c6c0081d1d2e47a21c"},"schema_version":"1.0"},"canonical_sha256":"77eabb7614a38e91896fa375bafc9a25bb8ae240070938ef51add89f8e5ef94d","source":{"kind":"arxiv","id":"1109.1528","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1109.1528","created_at":"2026-05-18T03:18:18Z"},{"alias_kind":"arxiv_version","alias_value":"1109.1528v3","created_at":"2026-05-18T03:18:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1109.1528","created_at":"2026-05-18T03:18:18Z"},{"alias_kind":"pith_short_12","alias_value":"O7VLW5QUUOHJ","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_16","alias_value":"O7VLW5QUUOHJDCLP","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_8","alias_value":"O7VLW5QU","created_at":"2026-05-18T12:26:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:O7VLW5QUUOHJDCLPUN23V7E2EW","target":"record","payload":{"canonical_record":{"source":{"id":"1109.1528","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2011-09-07T18:21:39Z","cross_cats_sorted":["cs.LG","cs.MA","nlin.AO","q-bio.PE"],"title_canon_sha256":"4eb355370797259484bd28214858619baf00cfb5fa529ece708e1e34cf0247e8","abstract_canon_sha256":"7ce20b666ee5f4f448bba1943920950e98d676aed1c678c6c0081d1d2e47a21c"},"schema_version":"1.0"},"canonical_sha256":"77eabb7614a38e91896fa375bafc9a25bb8ae240070938ef51add89f8e5ef94d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:18:18.783485Z","signature_b64":"CGePcbQ0+BSo8A2Dy7nkYGBhfYc3wfc26zcsZ5dMq+SYGCafR7t0bR77CY9xJJSvy/tayxjouHsSPQ7n8MKjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77eabb7614a38e91896fa375bafc9a25bb8ae240070938ef51add89f8e5ef94d","last_reissued_at":"2026-05-18T03:18:18.782830Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:18:18.782830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1109.1528","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:18:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qFk/qUm0+tiAN0sKXTL22+RfEIvPGlgH3jIHEbZvzvpVirUoTa5cwpHVlAexc/KzcdyQHpWh3FTubbUPR1cPDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T08:59:39.916469Z"},"content_sha256":"9dccf147c7e94f0fbc3732b6b87511a6b6d9067d43934a87797a5af334a45bed","schema_version":"1.0","event_id":"sha256:9dccf147c7e94f0fbc3732b6b87511a6b6d9067d43934a87797a5af334a45bed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:O7VLW5QUUOHJDCLPUN23V7E2EW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamics of Boltzmann Q-Learning in Two-Player Two-Action Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA","nlin.AO","q-bio.PE"],"primary_cat":"cs.GT","authors_text":"Aram Galstyan, Ardeshir Kianercy","submitted_at":"2011-09-07T18:21:39Z","abstract_excerpt":"We consider the dynamics of Q-learning in two-player two-action games with a Boltzmann exploration mechanism. For any non-zero exploration rate the dynamics is dissipative, which guarantees that agent strategies converge to rest points that are generally different from the game's Nash Equlibria (NE). We provide a comprehensive characterization of the rest point structure for different games, and examine the sensitivity of this structure with respect to the noise due to exploration. Our results indicate that for a class of games with multiple NE the asymptotic behavior of learning dynamics can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1109.1528","kind":"arxiv","version":3},"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":"2026-05-18T03:18:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cy2QLutTgf4j8e2DeSYgWMmb6K0mrKU/7tqvY8Scay/VXN93fMQvWw/e6Dx9/pP06jC2ZQHqm312hN7UI/h0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T08:59:39.916820Z"},"content_sha256":"55af687984e93d469ab0376691d8f2087b8c25c4a34ab251a8aa7016f89a5983","schema_version":"1.0","event_id":"sha256:55af687984e93d469ab0376691d8f2087b8c25c4a34ab251a8aa7016f89a5983"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW/bundle.json","state_url":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O7VLW5QUUOHJDCLPUN23V7E2EW/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":"2026-07-02T08:59:39Z","links":{"resolver":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW","bundle":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW/bundle.json","state":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O7VLW5QUUOHJDCLPUN23V7E2EW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:O7VLW5QUUOHJDCLPUN23V7E2EW","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":"7ce20b666ee5f4f448bba1943920950e98d676aed1c678c6c0081d1d2e47a21c","cross_cats_sorted":["cs.LG","cs.MA","nlin.AO","q-bio.PE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2011-09-07T18:21:39Z","title_canon_sha256":"4eb355370797259484bd28214858619baf00cfb5fa529ece708e1e34cf0247e8"},"schema_version":"1.0","source":{"id":"1109.1528","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1109.1528","created_at":"2026-05-18T03:18:18Z"},{"alias_kind":"arxiv_version","alias_value":"1109.1528v3","created_at":"2026-05-18T03:18:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1109.1528","created_at":"2026-05-18T03:18:18Z"},{"alias_kind":"pith_short_12","alias_value":"O7VLW5QUUOHJ","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_16","alias_value":"O7VLW5QUUOHJDCLP","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_8","alias_value":"O7VLW5QU","created_at":"2026-05-18T12:26:37Z"}],"graph_snapshots":[{"event_id":"sha256:55af687984e93d469ab0376691d8f2087b8c25c4a34ab251a8aa7016f89a5983","target":"graph","created_at":"2026-05-18T03:18:18Z","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":"We consider the dynamics of Q-learning in two-player two-action games with a Boltzmann exploration mechanism. For any non-zero exploration rate the dynamics is dissipative, which guarantees that agent strategies converge to rest points that are generally different from the game's Nash Equlibria (NE). We provide a comprehensive characterization of the rest point structure for different games, and examine the sensitivity of this structure with respect to the noise due to exploration. Our results indicate that for a class of games with multiple NE the asymptotic behavior of learning dynamics can ","authors_text":"Aram Galstyan, Ardeshir Kianercy","cross_cats":["cs.LG","cs.MA","nlin.AO","q-bio.PE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2011-09-07T18:21:39Z","title":"Dynamics of Boltzmann Q-Learning in Two-Player Two-Action Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1109.1528","kind":"arxiv","version":3},"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":"sha256:9dccf147c7e94f0fbc3732b6b87511a6b6d9067d43934a87797a5af334a45bed","target":"record","created_at":"2026-05-18T03:18:18Z","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":"7ce20b666ee5f4f448bba1943920950e98d676aed1c678c6c0081d1d2e47a21c","cross_cats_sorted":["cs.LG","cs.MA","nlin.AO","q-bio.PE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2011-09-07T18:21:39Z","title_canon_sha256":"4eb355370797259484bd28214858619baf00cfb5fa529ece708e1e34cf0247e8"},"schema_version":"1.0","source":{"id":"1109.1528","kind":"arxiv","version":3}},"canonical_sha256":"77eabb7614a38e91896fa375bafc9a25bb8ae240070938ef51add89f8e5ef94d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77eabb7614a38e91896fa375bafc9a25bb8ae240070938ef51add89f8e5ef94d","first_computed_at":"2026-05-18T03:18:18.782830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:18:18.782830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CGePcbQ0+BSo8A2Dy7nkYGBhfYc3wfc26zcsZ5dMq+SYGCafR7t0bR77CY9xJJSvy/tayxjouHsSPQ7n8MKjCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:18:18.783485Z","signed_message":"canonical_sha256_bytes"},"source_id":"1109.1528","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dccf147c7e94f0fbc3732b6b87511a6b6d9067d43934a87797a5af334a45bed","sha256:55af687984e93d469ab0376691d8f2087b8c25c4a34ab251a8aa7016f89a5983"],"state_sha256":"d3afe20a57eadf3df4fd0ff7fb4c1b71760620ebf2d7eeaa18fc2670001711fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2EkgKJKuC5biIg7SxoR15LMH8N0tIygsNTP1kNBmZXhImA5KpXjaHUJvk7RJwoi2aKjrYlfurhIvnye6BDSLCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T08:59:39.918779Z","bundle_sha256":"e03d28a119d1230542a17e0edca8680125ef916be73f713eb7eaabdd257d21ac"}}