{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:O7VLW5QUUOHJDCLPUN23V7E2EW","short_pith_number":"pith:O7VLW5QU","schema_version":"1.0","canonical_sha256":"77eabb7614a38e91896fa375bafc9a25bb8ae240070938ef51add89f8e5ef94d","source":{"kind":"arxiv","id":"1109.1528","version":3},"attestation_state":"computed","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 "},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1109.1528","created_at":"2026-05-18T03:18:18.782933+00:00"},{"alias_kind":"arxiv_version","alias_value":"1109.1528v3","created_at":"2026-05-18T03:18:18.782933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1109.1528","created_at":"2026-05-18T03:18:18.782933+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7VLW5QUUOHJ","created_at":"2026-05-18T12:26:37.096874+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7VLW5QUUOHJDCLP","created_at":"2026-05-18T12:26:37.096874+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7VLW5QU","created_at":"2026-05-18T12:26:37.096874+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/O7VLW5QUUOHJDCLPUN23V7E2EW","json":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW.json","graph_json":"https://pith.science/api/pith-number/O7VLW5QUUOHJDCLPUN23V7E2EW/graph.json","events_json":"https://pith.science/api/pith-number/O7VLW5QUUOHJDCLPUN23V7E2EW/events.json","paper":"https://pith.science/paper/O7VLW5QU"},"agent_actions":{"view_html":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW","download_json":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW.json","view_paper":"https://pith.science/paper/O7VLW5QU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1109.1528&json=true","fetch_graph":"https://pith.science/api/pith-number/O7VLW5QUUOHJDCLPUN23V7E2EW/graph.json","fetch_events":"https://pith.science/api/pith-number/O7VLW5QUUOHJDCLPUN23V7E2EW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW/action/storage_attestation","attest_author":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW/action/author_attestation","sign_citation":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW/action/citation_signature","submit_replication":"https://pith.science/pith/O7VLW5QUUOHJDCLPUN23V7E2EW/action/replication_record"}},"created_at":"2026-05-18T03:18:18.782933+00:00","updated_at":"2026-05-18T03:18:18.782933+00:00"}