{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4SH3WVGMFABBS3GG4UIF3J4EDZ","short_pith_number":"pith:4SH3WVGM","schema_version":"1.0","canonical_sha256":"e48fbb54cc2802196cc6e5105da7841e5d0edbb36a2eee316252b63ce060cdc7","source":{"kind":"arxiv","id":"1703.01310","version":2},"attestation_state":"computed","paper":{"title":"Count-Based Exploration with Neural Density Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aaron van den Oord, Georg Ostrovski, Marc G. Bellemare, Remi Munos","submitted_at":"2017-03-03T19:07:53Z","abstract_excerpt":"Bellemare et al. (2016) introduced the notion of a pseudo-count, derived from a density model, to generalize count-based exploration to non-tabular reinforcement learning. This pseudo-count was used to generate an exploration bonus for a DQN agent and combined with a mixed Monte Carlo update was sufficient to achieve state of the art on the Atari 2600 game Montezuma's Revenge. We consider two questions left open by their work: First, how important is the quality of the density model for exploration? Second, what role does the Monte Carlo update play in exploration? We answer the first question"},"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":"1703.01310","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T19:07:53Z","cross_cats_sorted":[],"title_canon_sha256":"e9836eee740407c96bc73456a38ccb344540f8a6930c456d30a4287409afef99","abstract_canon_sha256":"33a6a9a8e24577b94b731aacd67701450d7cb0ef341323f2cdfb9d8330ed0e7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:23.502003Z","signature_b64":"bvq4y1mqVHMnGy3A/r9h40Vu7UDawLlKmeskqKlpcotGR0LlFth29ITXOtCdscZovHwShrimhvMEZOQmauWkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e48fbb54cc2802196cc6e5105da7841e5d0edbb36a2eee316252b63ce060cdc7","last_reissued_at":"2026-05-18T00:42:23.501622Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:23.501622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Count-Based Exploration with Neural Density Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aaron van den Oord, Georg Ostrovski, Marc G. Bellemare, Remi Munos","submitted_at":"2017-03-03T19:07:53Z","abstract_excerpt":"Bellemare et al. (2016) introduced the notion of a pseudo-count, derived from a density model, to generalize count-based exploration to non-tabular reinforcement learning. This pseudo-count was used to generate an exploration bonus for a DQN agent and combined with a mixed Monte Carlo update was sufficient to achieve state of the art on the Atari 2600 game Montezuma's Revenge. We consider two questions left open by their work: First, how important is the quality of the density model for exploration? Second, what role does the Monte Carlo update play in exploration? We answer the first question"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01310","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":"1703.01310","created_at":"2026-05-18T00:42:23.501680+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.01310v2","created_at":"2026-05-18T00:42:23.501680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01310","created_at":"2026-05-18T00:42:23.501680+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SH3WVGMFABB","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SH3WVGMFABBS3GG","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SH3WVGM","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06143","citing_title":"Neural Embedding for Physical Manipulations","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ","json":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ.json","graph_json":"https://pith.science/api/pith-number/4SH3WVGMFABBS3GG4UIF3J4EDZ/graph.json","events_json":"https://pith.science/api/pith-number/4SH3WVGMFABBS3GG4UIF3J4EDZ/events.json","paper":"https://pith.science/paper/4SH3WVGM"},"agent_actions":{"view_html":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ","download_json":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ.json","view_paper":"https://pith.science/paper/4SH3WVGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.01310&json=true","fetch_graph":"https://pith.science/api/pith-number/4SH3WVGMFABBS3GG4UIF3J4EDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4SH3WVGMFABBS3GG4UIF3J4EDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ/action/storage_attestation","attest_author":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ/action/author_attestation","sign_citation":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ/action/citation_signature","submit_replication":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ/action/replication_record"}},"created_at":"2026-05-18T00:42:23.501680+00:00","updated_at":"2026-05-18T00:42:23.501680+00:00"}