{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5WF3HFN7YL7NA2OPBW5KUF6FFI","short_pith_number":"pith:5WF3HFN7","schema_version":"1.0","canonical_sha256":"ed8bb395bfc2fed069cf0dbaaa17c52a252fa88f31acd78e765771d1734f480e","source":{"kind":"arxiv","id":"1802.02277","version":2},"attestation_state":"computed","paper":{"title":"From Game-theoretic Multi-agent Log Linear Learning to Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Lacra Pavel, Mohammadhosein Hasanbeig","submitted_at":"2018-02-07T01:22:13Z","abstract_excerpt":"The main focus of this paper is on enhancement of two types of game-theoretic learning algorithms: log-linear learning and reinforcement learning. The standard analysis of log-linear learning needs a highly structured environment, i.e. strong assumptions about the game from an implementation perspective. In this paper, we introduce a variant of log-linear learning that provides asymptotic guarantees while relaxing the structural assumptions to include synchronous updates and limitations in information available to the players. On the other hand, model-free reinforcement learning is able to per"},"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":"1802.02277","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-07T01:22:13Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"f825e83993a634654025209c85813582433de68851663ca705a268fe9b59f63d","abstract_canon_sha256":"9331c434d525d11f9a66cd4bb235eac01d3ba8b1b39c9fbe3e586b772c8c8796"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:32.057554Z","signature_b64":"ltxhk0nW5mwlN4uw6J1dSH7G2bsi5d2psd18Q3pPqBEnKT5w/kZ2XEWtp5IBYN9MnSmiHJMjywO6dollL+hLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed8bb395bfc2fed069cf0dbaaa17c52a252fa88f31acd78e765771d1734f480e","last_reissued_at":"2026-05-18T00:05:32.057066Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:32.057066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Game-theoretic Multi-agent Log Linear Learning to Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Lacra Pavel, Mohammadhosein Hasanbeig","submitted_at":"2018-02-07T01:22:13Z","abstract_excerpt":"The main focus of this paper is on enhancement of two types of game-theoretic learning algorithms: log-linear learning and reinforcement learning. The standard analysis of log-linear learning needs a highly structured environment, i.e. strong assumptions about the game from an implementation perspective. In this paper, we introduce a variant of log-linear learning that provides asymptotic guarantees while relaxing the structural assumptions to include synchronous updates and limitations in information available to the players. On the other hand, model-free reinforcement learning is able to per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.02277","kind":"arxiv","version":2},"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":"1802.02277","created_at":"2026-05-18T00:05:32.057135+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.02277v2","created_at":"2026-05-18T00:05:32.057135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.02277","created_at":"2026-05-18T00:05:32.057135+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WF3HFN7YL7N","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WF3HFN7YL7NA2OP","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WF3HFN7","created_at":"2026-05-18T12:32:08.215937+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/5WF3HFN7YL7NA2OPBW5KUF6FFI","json":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI.json","graph_json":"https://pith.science/api/pith-number/5WF3HFN7YL7NA2OPBW5KUF6FFI/graph.json","events_json":"https://pith.science/api/pith-number/5WF3HFN7YL7NA2OPBW5KUF6FFI/events.json","paper":"https://pith.science/paper/5WF3HFN7"},"agent_actions":{"view_html":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI","download_json":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI.json","view_paper":"https://pith.science/paper/5WF3HFN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.02277&json=true","fetch_graph":"https://pith.science/api/pith-number/5WF3HFN7YL7NA2OPBW5KUF6FFI/graph.json","fetch_events":"https://pith.science/api/pith-number/5WF3HFN7YL7NA2OPBW5KUF6FFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI/action/storage_attestation","attest_author":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI/action/author_attestation","sign_citation":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI/action/citation_signature","submit_replication":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI/action/replication_record"}},"created_at":"2026-05-18T00:05:32.057135+00:00","updated_at":"2026-05-18T00:05:32.057135+00:00"}