{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GCMJFQQYI2WPD3U4RID7S45G54","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":"f347d381bad10e9ff6adbc55644a43059a8ac9424c160200ea2795329924478a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T18:15:44Z","title_canon_sha256":"e6c9c2b7911b0d1f29574e1fa2706bbc4c7206b5049da0c7c1d882ba30f420af"},"schema_version":"1.0","source":{"id":"1812.02690","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02690","created_at":"2026-05-17T23:55:30Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02690v2","created_at":"2026-05-17T23:55:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02690","created_at":"2026-05-17T23:55:30Z"},{"alias_kind":"pith_short_12","alias_value":"GCMJFQQYI2WP","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GCMJFQQYI2WPD3U4","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GCMJFQQY","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:4bab984cd2f3e1f8629ca8f4dbaf248b4959c45c6fc7c2ee1ebfb5337f23035a","target":"graph","created_at":"2026-05-17T23:55:30Z","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":"Suppose an agent is in a (possibly unknown) Markov Decision Process in the absence of a reward signal, what might we hope that an agent can efficiently learn to do? This work studies a broad class of objectives that are defined solely as functions of the state-visitation frequencies that are induced by how the agent behaves. For example, one natural, intrinsically defined, objective problem is for the agent to learn a policy which induces a distribution over state space that is as uniform as possible, which can be measured in an entropic sense. We provide an efficient algorithm to optimize suc","authors_text":"Abby Van Soest, Elad Hazan, Karan Singh, Sham M. Kakade","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T18:15:44Z","title":"Provably Efficient Maximum Entropy Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02690","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:f34ca91f9b7e320990e2d4561278377982abb95cb6cbc1f77f5ddf28396c9a29","target":"record","created_at":"2026-05-17T23:55:30Z","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":"f347d381bad10e9ff6adbc55644a43059a8ac9424c160200ea2795329924478a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T18:15:44Z","title_canon_sha256":"e6c9c2b7911b0d1f29574e1fa2706bbc4c7206b5049da0c7c1d882ba30f420af"},"schema_version":"1.0","source":{"id":"1812.02690","kind":"arxiv","version":2}},"canonical_sha256":"309892c21846acf1ee9c8a07f973a6ef3131cbef58ce97184f208c4ebf1ddf4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"309892c21846acf1ee9c8a07f973a6ef3131cbef58ce97184f208c4ebf1ddf4a","first_computed_at":"2026-05-17T23:55:30.717657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:30.717657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UZpwU45H3CqbX94EYwlTbETKTT8pPuMlPZ/JQhB4H3nnIdsr2FZ/Bmo/6oPmNL2FNBe3mVwU39Yw3Z1uJvHNDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:30.718107Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.02690","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f34ca91f9b7e320990e2d4561278377982abb95cb6cbc1f77f5ddf28396c9a29","sha256:4bab984cd2f3e1f8629ca8f4dbaf248b4959c45c6fc7c2ee1ebfb5337f23035a"],"state_sha256":"b10be7f90ef8ad641652989b15076711a23ebbe6b0c3a5f0e35aa1c2e3672e5b"}