{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DUP6OSESZKLAQTK7BTM2Y7DLXU","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":"e67372c2c6e15aa2eda5485f7c3730c8c13ef7e5494cf850b2bca49562cf52cb","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T14:21:53Z","title_canon_sha256":"332286d8c4f413c9a9664f97fa64cb07773abb24e43759e65e238f040f74ed9f"},"schema_version":"1.0","source":{"id":"1804.04012","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.04012","created_at":"2026-05-18T00:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"1804.04012v1","created_at":"2026-05-18T00:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04012","created_at":"2026-05-18T00:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"DUP6OSESZKLA","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DUP6OSESZKLAQTK7","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DUP6OSES","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:dd53187d3db8ef4287480f1df54406cb664eb7ecdf515cb86090fd66454263c6","target":"graph","created_at":"2026-05-18T00:18:42Z","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":"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","authors_text":"Leshem Choshen, Lior Fox, Yonatan Loewenstein","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T14:21:53Z","title":"DORA The Explorer: Directed Outreaching Reinforcement Action-Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04012","kind":"arxiv","version":1},"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":"sha256:6a046f0297bfae533d8c7e8ed25144b7c30b4c28c475893879734f4433ce5377","target":"record","created_at":"2026-05-18T00:18:42Z","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":"e67372c2c6e15aa2eda5485f7c3730c8c13ef7e5494cf850b2bca49562cf52cb","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T14:21:53Z","title_canon_sha256":"332286d8c4f413c9a9664f97fa64cb07773abb24e43759e65e238f040f74ed9f"},"schema_version":"1.0","source":{"id":"1804.04012","kind":"arxiv","version":1}},"canonical_sha256":"1d1fe74892ca96084d5f0cd9ac7c6bbd22da114e9247aedb32f9e5f958eadacd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d1fe74892ca96084d5f0cd9ac7c6bbd22da114e9247aedb32f9e5f958eadacd","first_computed_at":"2026-05-18T00:18:42.380617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:42.380617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z/vdupk8KId3h1poho0+KH8Dlv3VM9SPRYJovvtOMrkdLVgQgdgJ/sUMemKYeqUCrMpZqPnutC6DAPUjBpB6DA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:42.381300Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.04012","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a046f0297bfae533d8c7e8ed25144b7c30b4c28c475893879734f4433ce5377","sha256:dd53187d3db8ef4287480f1df54406cb664eb7ecdf515cb86090fd66454263c6"],"state_sha256":"b091c58090c528ce573930e547b98419dff9844fa3fd157f62b76a86d85c06cf"}