{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:J54V66PV4EU2EQ6MTQFOGSDHNT","short_pith_number":"pith:J54V66PV","schema_version":"1.0","canonical_sha256":"4f795f79f5e129a243cc9c0ae348676cfcdb594908651849f8e5076faf8bff91","source":{"kind":"arxiv","id":"1507.04296","version":2},"attestation_state":"computed","paper":{"title":"Massively Parallel Methods for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.NE"],"primary_cat":"cs.LG","authors_text":"Alessandro De Maria, Arun Nair, Cagdas Alcicek, Charles Beattie, David Silver, Koray Kavukcuoglu, Mustafa Suleyman, Praveen Srinivasan, Rory Fearon, Sam Blackwell, Shane Legg, Stig Petersen, Vedavyas Panneershelvam, Volodymyr Mnih","submitted_at":"2015-07-15T16:56:56Z","abstract_excerpt":"We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from stored experience; a distributed neural network to represent the value function or behaviour policy; and a distributed store of experience. We used our architecture to implement the Deep Q-Network algorithm (DQN). Our distributed algorithm was applied to 49 games from Atari 2600 games from the Arcade Learning Environment, using identical hyperparameters. Our performance surpasse"},"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":"1507.04296","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-15T16:56:56Z","cross_cats_sorted":["cs.AI","cs.DC","cs.NE"],"title_canon_sha256":"239ac75310d89dc45e0e22c98bb581b363f6174d72a5a6e47c58caacca508962","abstract_canon_sha256":"bde7497031978bf24896d5e912566ba5bdb6ad59fdff3e8a60d6f753dd0b105b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:47.627487Z","signature_b64":"QDgzGyB0uZSPo9vwXHkua817kxn/T9IDGjjliQj5zQIL/zCNd56x7Sb57Fj3IkvYyqw4WwNPuCVTESWjka1QDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f795f79f5e129a243cc9c0ae348676cfcdb594908651849f8e5076faf8bff91","last_reissued_at":"2026-05-18T01:36:47.626824Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:47.626824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Massively Parallel Methods for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.NE"],"primary_cat":"cs.LG","authors_text":"Alessandro De Maria, Arun Nair, Cagdas Alcicek, Charles Beattie, David Silver, Koray Kavukcuoglu, Mustafa Suleyman, Praveen Srinivasan, Rory Fearon, Sam Blackwell, Shane Legg, Stig Petersen, Vedavyas Panneershelvam, Volodymyr Mnih","submitted_at":"2015-07-15T16:56:56Z","abstract_excerpt":"We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from stored experience; a distributed neural network to represent the value function or behaviour policy; and a distributed store of experience. We used our architecture to implement the Deep Q-Network algorithm (DQN). Our distributed algorithm was applied to 49 games from Atari 2600 games from the Arcade Learning Environment, using identical hyperparameters. Our performance surpasse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.04296","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":"1507.04296","created_at":"2026-05-18T01:36:47.626933+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.04296v2","created_at":"2026-05-18T01:36:47.626933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.04296","created_at":"2026-05-18T01:36:47.626933+00:00"},{"alias_kind":"pith_short_12","alias_value":"J54V66PV4EU2","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_16","alias_value":"J54V66PV4EU2EQ6M","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_8","alias_value":"J54V66PV","created_at":"2026-05-18T12:29:27.538025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.08879","citing_title":"Placeto: Learning Generalizable Device Placement Algorithms for Distributed Machine Learning","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"1911.08265","citing_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT","json":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT.json","graph_json":"https://pith.science/api/pith-number/J54V66PV4EU2EQ6MTQFOGSDHNT/graph.json","events_json":"https://pith.science/api/pith-number/J54V66PV4EU2EQ6MTQFOGSDHNT/events.json","paper":"https://pith.science/paper/J54V66PV"},"agent_actions":{"view_html":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT","download_json":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT.json","view_paper":"https://pith.science/paper/J54V66PV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.04296&json=true","fetch_graph":"https://pith.science/api/pith-number/J54V66PV4EU2EQ6MTQFOGSDHNT/graph.json","fetch_events":"https://pith.science/api/pith-number/J54V66PV4EU2EQ6MTQFOGSDHNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT/action/storage_attestation","attest_author":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT/action/author_attestation","sign_citation":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT/action/citation_signature","submit_replication":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT/action/replication_record"}},"created_at":"2026-05-18T01:36:47.626933+00:00","updated_at":"2026-05-18T01:36:47.626933+00:00"}