{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5WF3HFN7YL7NA2OPBW5KUF6FFI","short_pith_number":"pith:5WF3HFN7","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"},"canonical_sha256":"ed8bb395bfc2fed069cf0dbaaa17c52a252fa88f31acd78e765771d1734f480e","source":{"kind":"arxiv","id":"1802.02277","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.02277","created_at":"2026-05-18T00:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"1802.02277v2","created_at":"2026-05-18T00:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.02277","created_at":"2026-05-18T00:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"5WF3HFN7YL7N","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5WF3HFN7YL7NA2OP","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5WF3HFN7","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5WF3HFN7YL7NA2OPBW5KUF6FFI","target":"record","payload":{"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"},"canonical_sha256":"ed8bb395bfc2fed069cf0dbaaa17c52a252fa88f31acd78e765771d1734f480e","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"},"source_kind":"arxiv","source_id":"1802.02277","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U8irKQrrtAv8p9lOjeJWq6U0qUgYPu0R7TQJrDZApUaIGyBez8w2uVjlzI9qvroOJaBusjkqfDVHGHIION8UDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T23:39:33.126446Z"},"content_sha256":"94975bc3a130755cae3cf1783e1e4d76de45502cc6c15ad6be836171d9df591d","schema_version":"1.0","event_id":"sha256:94975bc3a130755cae3cf1783e1e4d76de45502cc6c15ad6be836171d9df591d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5WF3HFN7YL7NA2OPBW5KUF6FFI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r00qQc+kOcRiZuCWcOutYqZd2fmcDVqSGxgUzORieg+jEpRN3avC9c/2C8GmnQPXMxak4MLTdymdx4qH2kvGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T23:39:33.126792Z"},"content_sha256":"e41ce64dd42b066ff9df99a45a80866d76ee6e3f6a89cd08f682eb050623da8d","schema_version":"1.0","event_id":"sha256:e41ce64dd42b066ff9df99a45a80866d76ee6e3f6a89cd08f682eb050623da8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI/bundle.json","state_url":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI/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":"2026-06-01T23:39:33Z","links":{"resolver":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI","bundle":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI/bundle.json","state":"https://pith.science/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WF3HFN7YL7NA2OPBW5KUF6FFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5WF3HFN7YL7NA2OPBW5KUF6FFI","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":"9331c434d525d11f9a66cd4bb235eac01d3ba8b1b39c9fbe3e586b772c8c8796","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-07T01:22:13Z","title_canon_sha256":"f825e83993a634654025209c85813582433de68851663ca705a268fe9b59f63d"},"schema_version":"1.0","source":{"id":"1802.02277","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.02277","created_at":"2026-05-18T00:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"1802.02277v2","created_at":"2026-05-18T00:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.02277","created_at":"2026-05-18T00:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"5WF3HFN7YL7N","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5WF3HFN7YL7NA2OP","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5WF3HFN7","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:e41ce64dd42b066ff9df99a45a80866d76ee6e3f6a89cd08f682eb050623da8d","target":"graph","created_at":"2026-05-18T00:05:32Z","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":"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","authors_text":"Lacra Pavel, Mohammadhosein Hasanbeig","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-07T01:22:13Z","title":"From Game-theoretic Multi-agent Log Linear Learning to Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.02277","kind":"arxiv","version":2},"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":"sha256:94975bc3a130755cae3cf1783e1e4d76de45502cc6c15ad6be836171d9df591d","target":"record","created_at":"2026-05-18T00:05:32Z","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":"9331c434d525d11f9a66cd4bb235eac01d3ba8b1b39c9fbe3e586b772c8c8796","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-07T01:22:13Z","title_canon_sha256":"f825e83993a634654025209c85813582433de68851663ca705a268fe9b59f63d"},"schema_version":"1.0","source":{"id":"1802.02277","kind":"arxiv","version":2}},"canonical_sha256":"ed8bb395bfc2fed069cf0dbaaa17c52a252fa88f31acd78e765771d1734f480e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed8bb395bfc2fed069cf0dbaaa17c52a252fa88f31acd78e765771d1734f480e","first_computed_at":"2026-05-18T00:05:32.057066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:32.057066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ltxhk0nW5mwlN4uw6J1dSH7G2bsi5d2psd18Q3pPqBEnKT5w/kZ2XEWtp5IBYN9MnSmiHJMjywO6dollL+hLBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:32.057554Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.02277","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94975bc3a130755cae3cf1783e1e4d76de45502cc6c15ad6be836171d9df591d","sha256:e41ce64dd42b066ff9df99a45a80866d76ee6e3f6a89cd08f682eb050623da8d"],"state_sha256":"b23525a75754a5c209da2b5c01c3f033b1a5921e7e3bf399bb23e238ac92ee72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUhg/M0ih8MoQWzXGwSizyFFpUyCdeepf6JngzTRbbgp6vyvDj38DxBnoSn+VIhIoCXVDk1vv1EpwKZBsWz/CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T23:39:33.128775Z","bundle_sha256":"d4da6b641299ab8603ce27e522b012b09bd913c1f722634faf850db350239ed3"}}