{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LH2GS6VEUWYXUOIWIA7EV5OI7N","short_pith_number":"pith:LH2GS6VE","schema_version":"1.0","canonical_sha256":"59f4697aa4a5b17a3916403e4af5c8fb42265d5a0dad3c60ed5ad188ad3f521a","source":{"kind":"arxiv","id":"1712.00006","version":2},"attestation_state":"computed","paper":{"title":"Comparing Deep Reinforcement Learning and Evolutionary Methods in Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Osmar R. Zaiane, Shangtong Zhang","submitted_at":"2017-11-30T03:40:06Z","abstract_excerpt":"Reinforcement Learning and the Evolutionary Strategy are two major approaches in addressing complicated control problems. Both are strong contenders and have their own devotee communities. Both groups have been very active in developing new advances in their own domain and devising, in recent years, leading-edge techniques to address complex continuous control tasks. Here, in the context of Deep Reinforcement Learning, we formulate a parallelized version of the Proximal Policy Optimization method and a Deep Deterministic Policy Gradient method. Moreover, we conduct a thorough comparison betwee"},"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":"1712.00006","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-30T03:40:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c04847203a92848a03a350a0942a3a0380fbb08a82d85db901f10af798a61172","abstract_canon_sha256":"3001d23ea920dfe4ea0fb4b4f1e499783620c6e1a2de9ea45c8f23440a042a46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:50.741097Z","signature_b64":"fFUzIixEHOEAB0XiyhkJLtwq4z836UV/71FYrr0kqQ5nL0DLkR7AgfXgYmLFV7nEA1OBlRFL1Ccfr5ELTcehAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59f4697aa4a5b17a3916403e4af5c8fb42265d5a0dad3c60ed5ad188ad3f521a","last_reissued_at":"2026-05-18T00:21:50.740512Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:50.740512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparing Deep Reinforcement Learning and Evolutionary Methods in Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Osmar R. Zaiane, Shangtong Zhang","submitted_at":"2017-11-30T03:40:06Z","abstract_excerpt":"Reinforcement Learning and the Evolutionary Strategy are two major approaches in addressing complicated control problems. Both are strong contenders and have their own devotee communities. Both groups have been very active in developing new advances in their own domain and devising, in recent years, leading-edge techniques to address complex continuous control tasks. Here, in the context of Deep Reinforcement Learning, we formulate a parallelized version of the Proximal Policy Optimization method and a Deep Deterministic Policy Gradient method. Moreover, we conduct a thorough comparison betwee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00006","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":"1712.00006","created_at":"2026-05-18T00:21:50.740608+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.00006v2","created_at":"2026-05-18T00:21:50.740608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00006","created_at":"2026-05-18T00:21:50.740608+00:00"},{"alias_kind":"pith_short_12","alias_value":"LH2GS6VEUWYX","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LH2GS6VEUWYXUOIW","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LH2GS6VE","created_at":"2026-05-18T12:31:28.150371+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/LH2GS6VEUWYXUOIWIA7EV5OI7N","json":"https://pith.science/pith/LH2GS6VEUWYXUOIWIA7EV5OI7N.json","graph_json":"https://pith.science/api/pith-number/LH2GS6VEUWYXUOIWIA7EV5OI7N/graph.json","events_json":"https://pith.science/api/pith-number/LH2GS6VEUWYXUOIWIA7EV5OI7N/events.json","paper":"https://pith.science/paper/LH2GS6VE"},"agent_actions":{"view_html":"https://pith.science/pith/LH2GS6VEUWYXUOIWIA7EV5OI7N","download_json":"https://pith.science/pith/LH2GS6VEUWYXUOIWIA7EV5OI7N.json","view_paper":"https://pith.science/paper/LH2GS6VE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.00006&json=true","fetch_graph":"https://pith.science/api/pith-number/LH2GS6VEUWYXUOIWIA7EV5OI7N/graph.json","fetch_events":"https://pith.science/api/pith-number/LH2GS6VEUWYXUOIWIA7EV5OI7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LH2GS6VEUWYXUOIWIA7EV5OI7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LH2GS6VEUWYXUOIWIA7EV5OI7N/action/storage_attestation","attest_author":"https://pith.science/pith/LH2GS6VEUWYXUOIWIA7EV5OI7N/action/author_attestation","sign_citation":"https://pith.science/pith/LH2GS6VEUWYXUOIWIA7EV5OI7N/action/citation_signature","submit_replication":"https://pith.science/pith/LH2GS6VEUWYXUOIWIA7EV5OI7N/action/replication_record"}},"created_at":"2026-05-18T00:21:50.740608+00:00","updated_at":"2026-05-18T00:21:50.740608+00:00"}