{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:QGUAX5VXUWAGZ52LGBIMFVKIUF","short_pith_number":"pith:QGUAX5VX","schema_version":"1.0","canonical_sha256":"81a80bf6b7a5806cf74b3050c2d548a17de12c1aaba8d70d5810a35fff3bda83","source":{"kind":"arxiv","id":"1611.04717","version":3},"attestation_state":"computed","paper":{"title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Adam Stooke, Davis Foote, Filip De Turck, Haoran Tang, John Schulman, Pieter Abbeel, Rein Houthooft, Xi Chen, Yan Duan","submitted_at":"2016-11-15T06:42:24Z","abstract_excerpt":"Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision processes (MDPs). It is generally thought that count-based methods cannot be applied in high-dimensional state spaces, since most states will only occur once. Recent deep RL exploration strategies are able to deal with high-dimensional continuous state spaces through complex heuristics, often relying on optimism in the face of uncertainty or intrinsic motivation. In this work, we describe a surprising finding"},"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":"1611.04717","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-15T06:42:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"44c995d95d2ebf83168a334c26aeb1512795b28e79edc95fc42e88310f3b62eb","abstract_canon_sha256":"f532cae65df7164b0da2d43756a309389304277e965719605e35f92ad6994b9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:56.718149Z","signature_b64":"hMEAItPsdUZbjSVWKmLrKHhsNwbseL8fn7g6kEBFH7zhpVbi6wdhxLl5hELDkNFbdP99BrCCn8mGH2eqh5mSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81a80bf6b7a5806cf74b3050c2d548a17de12c1aaba8d70d5810a35fff3bda83","last_reissued_at":"2026-05-18T00:28:56.717488Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:56.717488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Adam Stooke, Davis Foote, Filip De Turck, Haoran Tang, John Schulman, Pieter Abbeel, Rein Houthooft, Xi Chen, Yan Duan","submitted_at":"2016-11-15T06:42:24Z","abstract_excerpt":"Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision processes (MDPs). It is generally thought that count-based methods cannot be applied in high-dimensional state spaces, since most states will only occur once. Recent deep RL exploration strategies are able to deal with high-dimensional continuous state spaces through complex heuristics, often relying on optimism in the face of uncertainty or intrinsic motivation. In this work, we describe a surprising finding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04717","kind":"arxiv","version":3},"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":"1611.04717","created_at":"2026-05-18T00:28:56.717600+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.04717v3","created_at":"2026-05-18T00:28:56.717600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04717","created_at":"2026-05-18T00:28:56.717600+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGUAX5VXUWAG","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGUAX5VXUWAGZ52L","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGUAX5VX","created_at":"2026-05-18T12:30:39.010887+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/QGUAX5VXUWAGZ52LGBIMFVKIUF","json":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF.json","graph_json":"https://pith.science/api/pith-number/QGUAX5VXUWAGZ52LGBIMFVKIUF/graph.json","events_json":"https://pith.science/api/pith-number/QGUAX5VXUWAGZ52LGBIMFVKIUF/events.json","paper":"https://pith.science/paper/QGUAX5VX"},"agent_actions":{"view_html":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF","download_json":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF.json","view_paper":"https://pith.science/paper/QGUAX5VX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.04717&json=true","fetch_graph":"https://pith.science/api/pith-number/QGUAX5VXUWAGZ52LGBIMFVKIUF/graph.json","fetch_events":"https://pith.science/api/pith-number/QGUAX5VXUWAGZ52LGBIMFVKIUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF/action/storage_attestation","attest_author":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF/action/author_attestation","sign_citation":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF/action/citation_signature","submit_replication":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF/action/replication_record"}},"created_at":"2026-05-18T00:28:56.717600+00:00","updated_at":"2026-05-18T00:28:56.717600+00:00"}