{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IWPBDFQ2VNMAFUWBJCIMLCSKST","short_pith_number":"pith:IWPBDFQ2","schema_version":"1.0","canonical_sha256":"459e11961aab5802d2c14890c58a4a94f7d6f4015b67fcfded8a7664145fe7d7","source":{"kind":"arxiv","id":"1805.11711","version":1},"attestation_state":"computed","paper":{"title":"Depth and nonlinearity induce implicit exploration for RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Justas Dauparas, Katja Hofmann, Ryota Tomioka","submitted_at":"2018-05-29T21:21:18Z","abstract_excerpt":"The question of how to explore, i.e., take actions with uncertain outcomes to learn about possible future rewards, is a key question in reinforcement learning (RL). Here, we show a surprising result: We show that Q-learning with nonlinear Q-function and no explicit exploration (i.e., a purely greedy policy) can learn several standard benchmark tasks, including mountain car, equally well as, or better than, the most commonly-used $\\epsilon$-greedy exploration. We carefully examine this result and show that both the depth of the Q-network and the type of nonlinearity are important to induce such"},"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":"1805.11711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T21:21:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d5643ac8edb19b1b0783beb38c9a8c218b4d24bbeab7e9d3153f6048ece0bfd3","abstract_canon_sha256":"8c84a592b2af3f4d90662d2a6a95ef99cb669119c22873f5caac5fdaf06788df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:36.837167Z","signature_b64":"toqWdoOYTed3VGiBmY+gdvzH7rcebPkXup0QpFMx8FrvaHtZmRRutp4tVFFsg3e1Xre4d0Ohic643k9RVkmOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"459e11961aab5802d2c14890c58a4a94f7d6f4015b67fcfded8a7664145fe7d7","last_reissued_at":"2026-05-18T00:14:36.836345Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:36.836345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Depth and nonlinearity induce implicit exploration for RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Justas Dauparas, Katja Hofmann, Ryota Tomioka","submitted_at":"2018-05-29T21:21:18Z","abstract_excerpt":"The question of how to explore, i.e., take actions with uncertain outcomes to learn about possible future rewards, is a key question in reinforcement learning (RL). Here, we show a surprising result: We show that Q-learning with nonlinear Q-function and no explicit exploration (i.e., a purely greedy policy) can learn several standard benchmark tasks, including mountain car, equally well as, or better than, the most commonly-used $\\epsilon$-greedy exploration. We carefully examine this result and show that both the depth of the Q-network and the type of nonlinearity are important to induce such"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11711","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":"1805.11711","created_at":"2026-05-18T00:14:36.836494+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11711v1","created_at":"2026-05-18T00:14:36.836494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11711","created_at":"2026-05-18T00:14:36.836494+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWPBDFQ2VNMA","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWPBDFQ2VNMAFUWB","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWPBDFQ2","created_at":"2026-05-18T12:32:31.084164+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/IWPBDFQ2VNMAFUWBJCIMLCSKST","json":"https://pith.science/pith/IWPBDFQ2VNMAFUWBJCIMLCSKST.json","graph_json":"https://pith.science/api/pith-number/IWPBDFQ2VNMAFUWBJCIMLCSKST/graph.json","events_json":"https://pith.science/api/pith-number/IWPBDFQ2VNMAFUWBJCIMLCSKST/events.json","paper":"https://pith.science/paper/IWPBDFQ2"},"agent_actions":{"view_html":"https://pith.science/pith/IWPBDFQ2VNMAFUWBJCIMLCSKST","download_json":"https://pith.science/pith/IWPBDFQ2VNMAFUWBJCIMLCSKST.json","view_paper":"https://pith.science/paper/IWPBDFQ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11711&json=true","fetch_graph":"https://pith.science/api/pith-number/IWPBDFQ2VNMAFUWBJCIMLCSKST/graph.json","fetch_events":"https://pith.science/api/pith-number/IWPBDFQ2VNMAFUWBJCIMLCSKST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWPBDFQ2VNMAFUWBJCIMLCSKST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWPBDFQ2VNMAFUWBJCIMLCSKST/action/storage_attestation","attest_author":"https://pith.science/pith/IWPBDFQ2VNMAFUWBJCIMLCSKST/action/author_attestation","sign_citation":"https://pith.science/pith/IWPBDFQ2VNMAFUWBJCIMLCSKST/action/citation_signature","submit_replication":"https://pith.science/pith/IWPBDFQ2VNMAFUWBJCIMLCSKST/action/replication_record"}},"created_at":"2026-05-18T00:14:36.836494+00:00","updated_at":"2026-05-18T00:14:36.836494+00:00"}