{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MO2K7L7RI42HC6Y6D2YWG6RZ7S","short_pith_number":"pith:MO2K7L7R","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"},"canonical_sha256":"63b4afaff14734717b1e1eb1637a39fcbfda88d741016fceb779cf914b8b6276","source":{"kind":"arxiv","id":"1803.00933","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.00933","created_at":"2026-05-18T00:22:07Z"},{"alias_kind":"arxiv_version","alias_value":"1803.00933v1","created_at":"2026-05-18T00:22:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00933","created_at":"2026-05-18T00:22:07Z"},{"alias_kind":"pith_short_12","alias_value":"MO2K7L7RI42H","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MO2K7L7RI42HC6Y6","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MO2K7L7R","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MO2K7L7RI42HC6Y6D2YWG6RZ7S","target":"record","payload":{"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"},"canonical_sha256":"63b4afaff14734717b1e1eb1637a39fcbfda88d741016fceb779cf914b8b6276","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"},"source_kind":"arxiv","source_id":"1803.00933","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"61Ok1z6sxpbUuGEiAVR+Uul5vG9R+b+5nAZi+nReVGUdy5IgwnJE/WuXnTFyqBtDkvfiFF/c4aiRhMymzWXGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:32:03.876301Z"},"content_sha256":"588ce40f6a1042e11a1cf676ff208187c466e6daebc451f453b37e2a5f642ab5","schema_version":"1.0","event_id":"sha256:588ce40f6a1042e11a1cf676ff208187c466e6daebc451f453b37e2a5f642ab5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MO2K7L7RI42HC6Y6D2YWG6RZ7S","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ab1PvIczLGI/URrwrXjX+32+rJxBkSrKZsX5h7cyp0AfEoZlWGwc9RRoV0H2sMyQnmZ4QruRe+cNzIfRAZ0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:32:03.877063Z"},"content_sha256":"0f6c7e51cce972e1d3d7823b07edf5c64cd63ca74e00c20a8ea23b67ec7856ea","schema_version":"1.0","event_id":"sha256:0f6c7e51cce972e1d3d7823b07edf5c64cd63ca74e00c20a8ea23b67ec7856ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S/bundle.json","state_url":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T09:32:03Z","links":{"resolver":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S","bundle":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S/bundle.json","state":"https://pith.science/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MO2K7L7RI42HC6Y6D2YWG6RZ7S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MO2K7L7RI42HC6Y6D2YWG6RZ7S","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"579a75908c81e1b415b10c81827e61563318d63902ddf25774f504b25dcb3140","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-02T16:21:46Z","title_canon_sha256":"8122c8c2f81575ef712c200b726710d51ca92fdd31e73b3614257580677c205b"},"schema_version":"1.0","source":{"id":"1803.00933","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.00933","created_at":"2026-05-18T00:22:07Z"},{"alias_kind":"arxiv_version","alias_value":"1803.00933v1","created_at":"2026-05-18T00:22:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00933","created_at":"2026-05-18T00:22:07Z"},{"alias_kind":"pith_short_12","alias_value":"MO2K7L7RI42H","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MO2K7L7RI42HC6Y6","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MO2K7L7R","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:0f6c7e51cce972e1d3d7823b07edf5c64cd63ca74e00c20a8ea23b67ec7856ea","target":"graph","created_at":"2026-05-18T00:22:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Dan Horgan, David Budden, David Silver, Gabriel Barth-Maron, Hado van Hasselt, John Quan, Matteo Hessel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-02T16:21:46Z","title":"Distributed Prioritized Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00933","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:588ce40f6a1042e11a1cf676ff208187c466e6daebc451f453b37e2a5f642ab5","target":"record","created_at":"2026-05-18T00:22:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"579a75908c81e1b415b10c81827e61563318d63902ddf25774f504b25dcb3140","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-02T16:21:46Z","title_canon_sha256":"8122c8c2f81575ef712c200b726710d51ca92fdd31e73b3614257580677c205b"},"schema_version":"1.0","source":{"id":"1803.00933","kind":"arxiv","version":1}},"canonical_sha256":"63b4afaff14734717b1e1eb1637a39fcbfda88d741016fceb779cf914b8b6276","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63b4afaff14734717b1e1eb1637a39fcbfda88d741016fceb779cf914b8b6276","first_computed_at":"2026-05-18T00:22:07.421615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:07.421615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g4C8aQ0jizn9qc9+j1kkan0Gutdww1TEhzeHmS6Wnoj3CEs5255Eu/y2d932XPG6Uhcp50CFTdwYCe2sR3ihDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:07.422232Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.00933","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:588ce40f6a1042e11a1cf676ff208187c466e6daebc451f453b37e2a5f642ab5","sha256:0f6c7e51cce972e1d3d7823b07edf5c64cd63ca74e00c20a8ea23b67ec7856ea"],"state_sha256":"3befdba666dc962493bd075cd1834f317627d55f626726380034852ff5b2f919"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uEqWuUPDE4Zr5IxQd3GHv1C3qBSU+KRHWtiLnpb4evl+AU/SE76zehZQXc74SAcfbt95ZQW6Bh39BrwSYkWpAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T09:32:03.880690Z","bundle_sha256":"9e4f6cf23c11d788a571d60b0c32803480535f8d01213aee5d0f9f4510d7dea6"}}