{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:FNU2Y4UAY3FSIP34JQ6HC5VDRZ","short_pith_number":"pith:FNU2Y4UA","schema_version":"1.0","canonical_sha256":"2b69ac7280c6cb243f7c4c3c7176a38e6b1b5698df2d51cfb9baaac53e7cce5a","source":{"kind":"arxiv","id":"1606.01868","version":2},"attestation_state":"computed","paper":{"title":"Unifying Count-Based Exploration and Intrinsic Motivation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"David Saxton, Georg Ostrovski, Marc G. Bellemare, Remi Munos, Sriram Srinivasan, Tom Schaul","submitted_at":"2016-06-06T19:21:32Z","abstract_excerpt":"We consider an agent's uncertainty about its environment and the problem of generalizing this uncertainty across observations. Specifically, we focus on the problem of exploration in non-tabular reinforcement learning. Drawing inspiration from the intrinsic motivation literature, we use density models to measure uncertainty, and propose a novel algorithm for deriving a pseudo-count from an arbitrary density model. This technique enables us to generalize count-based exploration algorithms to the non-tabular case. We apply our ideas to Atari 2600 games, providing sensible pseudo-counts from raw "},"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":"1606.01868","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-06T19:21:32Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"b86846479f6152f74b6c55e8eaeb300d2b967ca553a93280d826a8a095bfb5f9","abstract_canon_sha256":"99a3988ad395c1d4e9348001811bee393767e72f2e47d7afd6faf3a54f82b374"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:19.286052Z","signature_b64":"xZbzeIrCrkvL0KKgwwZgsPbRQzf3FA43vkKHJOwY8XNHsy/3yrx+WnGjm082bJaXM8YWDzOZp3nBcalVPOaiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b69ac7280c6cb243f7c4c3c7176a38e6b1b5698df2d51cfb9baaac53e7cce5a","last_reissued_at":"2026-05-18T00:11:19.285346Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:19.285346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Count-Based Exploration and Intrinsic Motivation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"David Saxton, Georg Ostrovski, Marc G. Bellemare, Remi Munos, Sriram Srinivasan, Tom Schaul","submitted_at":"2016-06-06T19:21:32Z","abstract_excerpt":"We consider an agent's uncertainty about its environment and the problem of generalizing this uncertainty across observations. Specifically, we focus on the problem of exploration in non-tabular reinforcement learning. Drawing inspiration from the intrinsic motivation literature, we use density models to measure uncertainty, and propose a novel algorithm for deriving a pseudo-count from an arbitrary density model. This technique enables us to generalize count-based exploration algorithms to the non-tabular case. We apply our ideas to Atari 2600 games, providing sensible pseudo-counts from raw "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.01868","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":"1606.01868","created_at":"2026-05-18T00:11:19.285461+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.01868v2","created_at":"2026-05-18T00:11:19.285461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.01868","created_at":"2026-05-18T00:11:19.285461+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNU2Y4UAY3FS","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNU2Y4UAY3FSIP34","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNU2Y4UA","created_at":"2026-05-18T12:30:15.759754+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":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNU2Y4UAY3FSIP34JQ6HC5VDRZ","json":"https://pith.science/pith/FNU2Y4UAY3FSIP34JQ6HC5VDRZ.json","graph_json":"https://pith.science/api/pith-number/FNU2Y4UAY3FSIP34JQ6HC5VDRZ/graph.json","events_json":"https://pith.science/api/pith-number/FNU2Y4UAY3FSIP34JQ6HC5VDRZ/events.json","paper":"https://pith.science/paper/FNU2Y4UA"},"agent_actions":{"view_html":"https://pith.science/pith/FNU2Y4UAY3FSIP34JQ6HC5VDRZ","download_json":"https://pith.science/pith/FNU2Y4UAY3FSIP34JQ6HC5VDRZ.json","view_paper":"https://pith.science/paper/FNU2Y4UA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.01868&json=true","fetch_graph":"https://pith.science/api/pith-number/FNU2Y4UAY3FSIP34JQ6HC5VDRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FNU2Y4UAY3FSIP34JQ6HC5VDRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNU2Y4UAY3FSIP34JQ6HC5VDRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNU2Y4UAY3FSIP34JQ6HC5VDRZ/action/storage_attestation","attest_author":"https://pith.science/pith/FNU2Y4UAY3FSIP34JQ6HC5VDRZ/action/author_attestation","sign_citation":"https://pith.science/pith/FNU2Y4UAY3FSIP34JQ6HC5VDRZ/action/citation_signature","submit_replication":"https://pith.science/pith/FNU2Y4UAY3FSIP34JQ6HC5VDRZ/action/replication_record"}},"created_at":"2026-05-18T00:11:19.285461+00:00","updated_at":"2026-05-18T00:11:19.285461+00:00"}