{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DUP6OSESZKLAQTK7BTM2Y7DLXU","short_pith_number":"pith:DUP6OSES","schema_version":"1.0","canonical_sha256":"1d1fe74892ca96084d5f0cd9ac7c6bbd22da114e9247aedb32f9e5f958eadacd","source":{"kind":"arxiv","id":"1804.04012","version":1},"attestation_state":"computed","paper":{"title":"DORA The Explorer: Directed Outreaching Reinforcement Action-Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Leshem Choshen, Lior Fox, Yonatan Loewenstein","submitted_at":"2018-04-11T14:21:53Z","abstract_excerpt":"Exploration is a fundamental aspect of Reinforcement Learning, typically implemented using stochastic action-selection. Exploration, however, can be more efficient if directed toward gaining new world knowledge. Visit-counters have been proven useful both in practice and in theory for directed exploration. However, a major limitation of counters is their locality. While there are a few model-based solutions to this shortcoming, a model-free approach is still missing. We propose $E$-values, a generalization of counters that can be used to evaluate the propagating exploratory value over state-ac"},"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":"1804.04012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T14:21:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"332286d8c4f413c9a9664f97fa64cb07773abb24e43759e65e238f040f74ed9f","abstract_canon_sha256":"e67372c2c6e15aa2eda5485f7c3730c8c13ef7e5494cf850b2bca49562cf52cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:42.381300Z","signature_b64":"z/vdupk8KId3h1poho0+KH8Dlv3VM9SPRYJovvtOMrkdLVgQgdgJ/sUMemKYeqUCrMpZqPnutC6DAPUjBpB6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d1fe74892ca96084d5f0cd9ac7c6bbd22da114e9247aedb32f9e5f958eadacd","last_reissued_at":"2026-05-18T00:18:42.380617Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:42.380617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DORA The Explorer: Directed Outreaching Reinforcement Action-Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Leshem Choshen, Lior Fox, Yonatan Loewenstein","submitted_at":"2018-04-11T14:21:53Z","abstract_excerpt":"Exploration is a fundamental aspect of Reinforcement Learning, typically implemented using stochastic action-selection. Exploration, however, can be more efficient if directed toward gaining new world knowledge. Visit-counters have been proven useful both in practice and in theory for directed exploration. However, a major limitation of counters is their locality. While there are a few model-based solutions to this shortcoming, a model-free approach is still missing. We propose $E$-values, a generalization of counters that can be used to evaluate the propagating exploratory value over state-ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04012","kind":"arxiv","version":1},"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":"1804.04012","created_at":"2026-05-18T00:18:42.380734+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.04012v1","created_at":"2026-05-18T00:18:42.380734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04012","created_at":"2026-05-18T00:18:42.380734+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUP6OSESZKLA","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUP6OSESZKLAQTK7","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUP6OSES","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12084","citing_title":"Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU","json":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU.json","graph_json":"https://pith.science/api/pith-number/DUP6OSESZKLAQTK7BTM2Y7DLXU/graph.json","events_json":"https://pith.science/api/pith-number/DUP6OSESZKLAQTK7BTM2Y7DLXU/events.json","paper":"https://pith.science/paper/DUP6OSES"},"agent_actions":{"view_html":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU","download_json":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU.json","view_paper":"https://pith.science/paper/DUP6OSES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.04012&json=true","fetch_graph":"https://pith.science/api/pith-number/DUP6OSESZKLAQTK7BTM2Y7DLXU/graph.json","fetch_events":"https://pith.science/api/pith-number/DUP6OSESZKLAQTK7BTM2Y7DLXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU/action/storage_attestation","attest_author":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU/action/author_attestation","sign_citation":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU/action/citation_signature","submit_replication":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU/action/replication_record"}},"created_at":"2026-05-18T00:18:42.380734+00:00","updated_at":"2026-05-18T00:18:42.380734+00:00"}