{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KTBPE4WASLLY6MH5M3XQZ6YGHL","short_pith_number":"pith:KTBPE4WA","schema_version":"1.0","canonical_sha256":"54c2f272c092d78f30fd66ef0cfb063ade0aa2fbe280b6127bb02f0cd24406b1","source":{"kind":"arxiv","id":"1705.04862","version":2},"attestation_state":"computed","paper":{"title":"Efficient Parallel Methods for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alfredo V. Clemente, Arjun Chandra, Humberto N. Castej\\'on","submitted_at":"2017-05-13T17:39:54Z","abstract_excerpt":"We propose a novel framework for efficient parallelization of deep reinforcement learning algorithms, enabling these algorithms to learn from multiple actors on a single machine. The framework is algorithm agnostic and can be applied to on-policy, off-policy, value based and policy gradient based algorithms. Given its inherent parallelism, the framework can be efficiently implemented on a GPU, allowing the usage of powerful models while significantly reducing training time. We demonstrate the effectiveness of our framework by implementing an advantage actor-critic algorithm on a GPU, using on-"},"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":"1705.04862","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-13T17:39:54Z","cross_cats_sorted":[],"title_canon_sha256":"f8aadcb45a23ff90790805b53b690d00577269e4ca77d05caf7b579894054df0","abstract_canon_sha256":"4350d31bde7cc0bddf14b85f487d5b73158c6d6b613439500365f898b126b524"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:22.881026Z","signature_b64":"1vyG8PbYTGjTcFVdHlX/+lX7rPOitABwzlm4uCOCE3syTuGmcDs8fyq8xtwgINFyL2FAOTRq/cHqbbHcJ4wNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54c2f272c092d78f30fd66ef0cfb063ade0aa2fbe280b6127bb02f0cd24406b1","last_reissued_at":"2026-05-18T00:44:22.880526Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:22.880526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Parallel Methods for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alfredo V. Clemente, Arjun Chandra, Humberto N. Castej\\'on","submitted_at":"2017-05-13T17:39:54Z","abstract_excerpt":"We propose a novel framework for efficient parallelization of deep reinforcement learning algorithms, enabling these algorithms to learn from multiple actors on a single machine. The framework is algorithm agnostic and can be applied to on-policy, off-policy, value based and policy gradient based algorithms. Given its inherent parallelism, the framework can be efficiently implemented on a GPU, allowing the usage of powerful models while significantly reducing training time. We demonstrate the effectiveness of our framework by implementing an advantage actor-critic algorithm on a GPU, using on-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04862","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":"1705.04862","created_at":"2026-05-18T00:44:22.880607+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.04862v2","created_at":"2026-05-18T00:44:22.880607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04862","created_at":"2026-05-18T00:44:22.880607+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTBPE4WASLLY","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTBPE4WASLLY6MH5","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTBPE4WA","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/KTBPE4WASLLY6MH5M3XQZ6YGHL","json":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL.json","graph_json":"https://pith.science/api/pith-number/KTBPE4WASLLY6MH5M3XQZ6YGHL/graph.json","events_json":"https://pith.science/api/pith-number/KTBPE4WASLLY6MH5M3XQZ6YGHL/events.json","paper":"https://pith.science/paper/KTBPE4WA"},"agent_actions":{"view_html":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL","download_json":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL.json","view_paper":"https://pith.science/paper/KTBPE4WA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.04862&json=true","fetch_graph":"https://pith.science/api/pith-number/KTBPE4WASLLY6MH5M3XQZ6YGHL/graph.json","fetch_events":"https://pith.science/api/pith-number/KTBPE4WASLLY6MH5M3XQZ6YGHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL/action/storage_attestation","attest_author":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL/action/author_attestation","sign_citation":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL/action/citation_signature","submit_replication":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL/action/replication_record"}},"created_at":"2026-05-18T00:44:22.880607+00:00","updated_at":"2026-05-18T00:44:22.880607+00:00"}