{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3TVHTK2QGBNEHAWNOK4LDPJ2XB","short_pith_number":"pith:3TVHTK2Q","schema_version":"1.0","canonical_sha256":"dcea79ab50305a4382cd72b8b1bd3ab87c72a966ddb1e016b4c497b9df48f79f","source":{"kind":"arxiv","id":"1706.01905","version":2},"attestation_state":"computed","paper":{"title":"Parameter Space Noise for Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marcin Andrychowicz, Matthias Plappert, Pieter Abbeel, Prafulla Dhariwal, Rein Houthooft, Richard Y. Chen, Szymon Sidor, Tamim Asfour, Xi Chen","submitted_at":"2017-06-06T18:09:29Z","abstract_excerpt":"Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a richer set of behaviors. Methods such as evolutionary strategies use parameter perturbations, but discard all temporal structure in the process and require significantly more samples. Combining parameter noise with traditional RL methods allows to combine the best of both worlds. We demonstrate that both off- and on-policy methods benefit from this app"},"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":"1706.01905","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-06T18:09:29Z","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"title_canon_sha256":"1bb7b1601fdbe2ec6b9e8376c261360c779227c84d3c366419a55ca98c5e4c0d","abstract_canon_sha256":"48a2d5d30ee407a07387ef8af557500b04a2e21886ae9fefc6b3b4d394acecea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:42.793960Z","signature_b64":"sUUkWMSSOVM9st/jIEfmDrHuwRhbn1SbRbTiogRwvcCxX3MkfiTJr3/GlCE3XmV60Zo30oSeKh2GE3uszsLPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcea79ab50305a4382cd72b8b1bd3ab87c72a966ddb1e016b4c497b9df48f79f","last_reissued_at":"2026-05-18T00:24:42.793340Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:42.793340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter Space Noise for Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marcin Andrychowicz, Matthias Plappert, Pieter Abbeel, Prafulla Dhariwal, Rein Houthooft, Richard Y. Chen, Szymon Sidor, Tamim Asfour, Xi Chen","submitted_at":"2017-06-06T18:09:29Z","abstract_excerpt":"Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a richer set of behaviors. Methods such as evolutionary strategies use parameter perturbations, but discard all temporal structure in the process and require significantly more samples. Combining parameter noise with traditional RL methods allows to combine the best of both worlds. We demonstrate that both off- and on-policy methods benefit from this app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01905","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":"1706.01905","created_at":"2026-05-18T00:24:42.793425+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.01905v2","created_at":"2026-05-18T00:24:42.793425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01905","created_at":"2026-05-18T00:24:42.793425+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TVHTK2QGBNE","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TVHTK2QGBNEHAWN","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TVHTK2Q","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2504.09365","citing_title":"Identifying Protein Co-regulatory Network Logic by Solving B-SAT Problems through Gate-based Quantum Computing","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2506.14648","citing_title":"SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TVHTK2QGBNEHAWNOK4LDPJ2XB","json":"https://pith.science/pith/3TVHTK2QGBNEHAWNOK4LDPJ2XB.json","graph_json":"https://pith.science/api/pith-number/3TVHTK2QGBNEHAWNOK4LDPJ2XB/graph.json","events_json":"https://pith.science/api/pith-number/3TVHTK2QGBNEHAWNOK4LDPJ2XB/events.json","paper":"https://pith.science/paper/3TVHTK2Q"},"agent_actions":{"view_html":"https://pith.science/pith/3TVHTK2QGBNEHAWNOK4LDPJ2XB","download_json":"https://pith.science/pith/3TVHTK2QGBNEHAWNOK4LDPJ2XB.json","view_paper":"https://pith.science/paper/3TVHTK2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.01905&json=true","fetch_graph":"https://pith.science/api/pith-number/3TVHTK2QGBNEHAWNOK4LDPJ2XB/graph.json","fetch_events":"https://pith.science/api/pith-number/3TVHTK2QGBNEHAWNOK4LDPJ2XB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TVHTK2QGBNEHAWNOK4LDPJ2XB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TVHTK2QGBNEHAWNOK4LDPJ2XB/action/storage_attestation","attest_author":"https://pith.science/pith/3TVHTK2QGBNEHAWNOK4LDPJ2XB/action/author_attestation","sign_citation":"https://pith.science/pith/3TVHTK2QGBNEHAWNOK4LDPJ2XB/action/citation_signature","submit_replication":"https://pith.science/pith/3TVHTK2QGBNEHAWNOK4LDPJ2XB/action/replication_record"}},"created_at":"2026-05-18T00:24:42.793425+00:00","updated_at":"2026-05-18T00:24:42.793425+00:00"}