{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GCMJFQQYI2WPD3U4RID7S45G54","short_pith_number":"pith:GCMJFQQY","schema_version":"1.0","canonical_sha256":"309892c21846acf1ee9c8a07f973a6ef3131cbef58ce97184f208c4ebf1ddf4a","source":{"kind":"arxiv","id":"1812.02690","version":2},"attestation_state":"computed","paper":{"title":"Provably Efficient Maximum Entropy Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abby Van Soest, Elad Hazan, Karan Singh, Sham M. Kakade","submitted_at":"2018-12-06T18:15:44Z","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"},"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":"1812.02690","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T18:15:44Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e6c9c2b7911b0d1f29574e1fa2706bbc4c7206b5049da0c7c1d882ba30f420af","abstract_canon_sha256":"f347d381bad10e9ff6adbc55644a43059a8ac9424c160200ea2795329924478a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:30.718107Z","signature_b64":"UZpwU45H3CqbX94EYwlTbETKTT8pPuMlPZ/JQhB4H3nnIdsr2FZ/Bmo/6oPmNL2FNBe3mVwU39Yw3Z1uJvHNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"309892c21846acf1ee9c8a07f973a6ef3131cbef58ce97184f208c4ebf1ddf4a","last_reissued_at":"2026-05-17T23:55:30.717657Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:30.717657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Efficient Maximum Entropy Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abby Van Soest, Elad Hazan, Karan Singh, Sham M. Kakade","submitted_at":"2018-12-06T18:15:44Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02690","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":"1812.02690","created_at":"2026-05-17T23:55:30.717724+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02690v2","created_at":"2026-05-17T23:55:30.717724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02690","created_at":"2026-05-17T23:55:30.717724+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCMJFQQYI2WP","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCMJFQQYI2WPD3U4","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCMJFQQY","created_at":"2026-05-18T12:32:25.280505+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/GCMJFQQYI2WPD3U4RID7S45G54","json":"https://pith.science/pith/GCMJFQQYI2WPD3U4RID7S45G54.json","graph_json":"https://pith.science/api/pith-number/GCMJFQQYI2WPD3U4RID7S45G54/graph.json","events_json":"https://pith.science/api/pith-number/GCMJFQQYI2WPD3U4RID7S45G54/events.json","paper":"https://pith.science/paper/GCMJFQQY"},"agent_actions":{"view_html":"https://pith.science/pith/GCMJFQQYI2WPD3U4RID7S45G54","download_json":"https://pith.science/pith/GCMJFQQYI2WPD3U4RID7S45G54.json","view_paper":"https://pith.science/paper/GCMJFQQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02690&json=true","fetch_graph":"https://pith.science/api/pith-number/GCMJFQQYI2WPD3U4RID7S45G54/graph.json","fetch_events":"https://pith.science/api/pith-number/GCMJFQQYI2WPD3U4RID7S45G54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCMJFQQYI2WPD3U4RID7S45G54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCMJFQQYI2WPD3U4RID7S45G54/action/storage_attestation","attest_author":"https://pith.science/pith/GCMJFQQYI2WPD3U4RID7S45G54/action/author_attestation","sign_citation":"https://pith.science/pith/GCMJFQQYI2WPD3U4RID7S45G54/action/citation_signature","submit_replication":"https://pith.science/pith/GCMJFQQYI2WPD3U4RID7S45G54/action/replication_record"}},"created_at":"2026-05-17T23:55:30.717724+00:00","updated_at":"2026-05-17T23:55:30.717724+00:00"}