{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MO2K7L7RI42HC6Y6D2YWG6RZ7S","short_pith_number":"pith:MO2K7L7R","schema_version":"1.0","canonical_sha256":"63b4afaff14734717b1e1eb1637a39fcbfda88d741016fceb779cf914b8b6276","source":{"kind":"arxiv","id":"1803.00933","version":1},"attestation_state":"computed","paper":{"title":"Distributed Prioritized Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dan Horgan, David Budden, David Silver, Gabriel Barth-Maron, Hado van Hasselt, John Quan, Matteo Hessel","submitted_at":"2018-03-02T16:21:46Z","abstract_excerpt":"We propose a distributed architecture for deep reinforcement learning at scale, that enables agents to learn effectively from orders of magnitude more data than previously possible. The algorithm decouples acting from learning: the actors interact with their own instances of the environment by selecting actions according to a shared neural network, and accumulate the resulting experience in a shared experience replay memory; the learner replays samples of experience and updates the neural network. The architecture relies on prioritized experience replay to focus only on the most significant da"},"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":"1803.00933","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-02T16:21:46Z","cross_cats_sorted":[],"title_canon_sha256":"8122c8c2f81575ef712c200b726710d51ca92fdd31e73b3614257580677c205b","abstract_canon_sha256":"579a75908c81e1b415b10c81827e61563318d63902ddf25774f504b25dcb3140"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:07.422232Z","signature_b64":"g4C8aQ0jizn9qc9+j1kkan0Gutdww1TEhzeHmS6Wnoj3CEs5255Eu/y2d932XPG6Uhcp50CFTdwYCe2sR3ihDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63b4afaff14734717b1e1eb1637a39fcbfda88d741016fceb779cf914b8b6276","last_reissued_at":"2026-05-18T00:22:07.421615Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:07.421615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Prioritized Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dan Horgan, David Budden, David Silver, Gabriel Barth-Maron, Hado van Hasselt, John Quan, Matteo Hessel","submitted_at":"2018-03-02T16:21:46Z","abstract_excerpt":"We propose a distributed architecture for deep reinforcement learning at scale, that enables agents to learn effectively from orders of magnitude more data than previously possible. The algorithm decouples acting from learning: the actors interact with their own instances of the environment by selecting actions according to a shared neural network, and accumulate the resulting experience in a shared experience replay memory; the learner replays samples of experience and updates the neural network. The architecture relies on prioritized experience replay to focus only on the most significant da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00933","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":"1803.00933","created_at":"2026-05-18T00:22:07.421705+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.00933v1","created_at":"2026-05-18T00:22:07.421705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00933","created_at":"2026-05-18T00:22:07.421705+00:00"},{"alias_kind":"pith_short_12","alias_value":"MO2K7L7RI42H","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MO2K7L7RI42HC6Y6","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MO2K7L7R","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"1906.08809","citing_title":"A Deep Reinforcement Learning Approach for Global Routing","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05300","citing_title":"Learning Safe Unlabeled Multi-Robot Planning with Motion Constraints","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08040","citing_title":"Convolutional Reservoir Computing for World Models","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2509.22963","citing_title":"Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2102.01293","citing_title":"Scaling Laws for Transfer","ref_index":122,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14043","citing_title":"Optimal design of solar-battery hybrid resources considering multi-market participation under weather and price uncertainty","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2010.02193","citing_title":"Mastering Atari with Discrete World Models","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"1912.06680","citing_title":"Dota 2 with Large Scale Deep Reinforcement Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":241,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S","json":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S.json","graph_json":"https://pith.science/api/pith-number/MO2K7L7RI42HC6Y6D2YWG6RZ7S/graph.json","events_json":"https://pith.science/api/pith-number/MO2K7L7RI42HC6Y6D2YWG6RZ7S/events.json","paper":"https://pith.science/paper/MO2K7L7R"},"agent_actions":{"view_html":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S","download_json":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S.json","view_paper":"https://pith.science/paper/MO2K7L7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.00933&json=true","fetch_graph":"https://pith.science/api/pith-number/MO2K7L7RI42HC6Y6D2YWG6RZ7S/graph.json","fetch_events":"https://pith.science/api/pith-number/MO2K7L7RI42HC6Y6D2YWG6RZ7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S/action/storage_attestation","attest_author":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S/action/author_attestation","sign_citation":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S/action/citation_signature","submit_replication":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S/action/replication_record"}},"created_at":"2026-05-18T00:22:07.421705+00:00","updated_at":"2026-05-18T00:22:07.421705+00:00"}