{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:JQARITQTBYZ2MGQWIKBBWOA4PQ","short_pith_number":"pith:JQARITQT","schema_version":"1.0","canonical_sha256":"4c01144e130e33a61a1642821b381c7c0990a1393eeefbf14969573d380dfc39","source":{"kind":"arxiv","id":"1409.8498","version":3},"attestation_state":"computed","paper":{"title":"Non-myopic learning in repeated stochastic games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.GT","authors_text":"Jacob W. Crandall","submitted_at":"2014-09-30T11:46:29Z","abstract_excerpt":"In repeated stochastic games (RSGs), an agent must quickly adapt to the behavior of previously unknown associates, who may themselves be learning. This machine-learning problem is particularly challenging due, in part, to the presence of multiple (even infinite) equilibria and inherently large strategy spaces. In this paper, we introduce a method to reduce the strategy space of two-player general-sum RSGs to a handful of expert strategies. This process, called Mega, effectually reduces an RSG to a bandit problem. We show that the resulting strategy space preserves several important properties "},"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":"1409.8498","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2014-09-30T11:46:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"38a309b3cdb64131c8d03df834786cbe86dfe4a0c272e7a4bcf05573f34f7a30","abstract_canon_sha256":"9ff19b1318e59643df43146e7915db53f668539db2e1d9d218972f5835049bf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:35.214076Z","signature_b64":"Z4uJ1Uc22njeB3d6IRGva1YXB5If6/r4cED8Omwz+L3Uub63OAlrJVGCcQlv7Ad5/+Q5SgPY6XqWR0QV/PNBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c01144e130e33a61a1642821b381c7c0990a1393eeefbf14969573d380dfc39","last_reissued_at":"2026-05-18T00:25:35.213438Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:35.213438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-myopic learning in repeated stochastic games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.GT","authors_text":"Jacob W. Crandall","submitted_at":"2014-09-30T11:46:29Z","abstract_excerpt":"In repeated stochastic games (RSGs), an agent must quickly adapt to the behavior of previously unknown associates, who may themselves be learning. This machine-learning problem is particularly challenging due, in part, to the presence of multiple (even infinite) equilibria and inherently large strategy spaces. In this paper, we introduce a method to reduce the strategy space of two-player general-sum RSGs to a handful of expert strategies. This process, called Mega, effectually reduces an RSG to a bandit problem. We show that the resulting strategy space preserves several important properties "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.8498","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":"1409.8498","created_at":"2026-05-18T00:25:35.213547+00:00"},{"alias_kind":"arxiv_version","alias_value":"1409.8498v3","created_at":"2026-05-18T00:25:35.213547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.8498","created_at":"2026-05-18T00:25:35.213547+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQARITQTBYZ2","created_at":"2026-05-18T12:28:35.611951+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQARITQTBYZ2MGQW","created_at":"2026-05-18T12:28:35.611951+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQARITQT","created_at":"2026-05-18T12:28:35.611951+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/JQARITQTBYZ2MGQWIKBBWOA4PQ","json":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ.json","graph_json":"https://pith.science/api/pith-number/JQARITQTBYZ2MGQWIKBBWOA4PQ/graph.json","events_json":"https://pith.science/api/pith-number/JQARITQTBYZ2MGQWIKBBWOA4PQ/events.json","paper":"https://pith.science/paper/JQARITQT"},"agent_actions":{"view_html":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ","download_json":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ.json","view_paper":"https://pith.science/paper/JQARITQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1409.8498&json=true","fetch_graph":"https://pith.science/api/pith-number/JQARITQTBYZ2MGQWIKBBWOA4PQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JQARITQTBYZ2MGQWIKBBWOA4PQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ/action/storage_attestation","attest_author":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ/action/author_attestation","sign_citation":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ/action/citation_signature","submit_replication":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ/action/replication_record"}},"created_at":"2026-05-18T00:25:35.213547+00:00","updated_at":"2026-05-18T00:25:35.213547+00:00"}