{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TACZA3OTAQQH4IEIKMVJWTULZO","short_pith_number":"pith:TACZA3OT","canonical_record":{"source":{"id":"1802.01561","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-05T18:47:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"457206bb96b574c4b1e16cb6477dead4082216e4e4788a9f3cc85b110a2aad07","abstract_canon_sha256":"7b982bad01d2e7d57b89bc0b15d6d44fb13ead0c0063d32b234bd66874ce9dcd"},"schema_version":"1.0"},"canonical_sha256":"9805906dd304207e2088532a9b4e8bcbb762c038e0bd961cb7b7a21ecc74b0bd","source":{"kind":"arxiv","id":"1802.01561","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.01561","created_at":"2026-05-18T00:12:08Z"},{"alias_kind":"arxiv_version","alias_value":"1802.01561v3","created_at":"2026-05-18T00:12:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.01561","created_at":"2026-05-18T00:12:08Z"},{"alias_kind":"pith_short_12","alias_value":"TACZA3OTAQQH","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TACZA3OTAQQH4IEI","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TACZA3OT","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TACZA3OTAQQH4IEIKMVJWTULZO","target":"record","payload":{"canonical_record":{"source":{"id":"1802.01561","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-05T18:47:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"457206bb96b574c4b1e16cb6477dead4082216e4e4788a9f3cc85b110a2aad07","abstract_canon_sha256":"7b982bad01d2e7d57b89bc0b15d6d44fb13ead0c0063d32b234bd66874ce9dcd"},"schema_version":"1.0"},"canonical_sha256":"9805906dd304207e2088532a9b4e8bcbb762c038e0bd961cb7b7a21ecc74b0bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:08.949583Z","signature_b64":"t18uvJqTEUJCIA+8RP95CuoTRrBz5Aca7Wx3dxVsDJxhZue2/7GdggS4UuAxp/fj8TICgGcijD34cVjIOr5IAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9805906dd304207e2088532a9b4e8bcbb762c038e0bd961cb7b7a21ecc74b0bd","last_reissued_at":"2026-05-18T00:12:08.949103Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:08.949103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.01561","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:12:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oAZ0/AQwo8WQ+Rf9/OxVgAQcCOQWKOBhYa6bQbnZO6+HG7W/v/9dqIXKNzTWjpPfhNSnwpwRf3Yns5GXzMTIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T06:39:03.312851Z"},"content_sha256":"eccaa57d498fca9cbaa79bbc72a4a4ffb4cf77a9c95d187eea8d059c2ecbae11","schema_version":"1.0","event_id":"sha256:eccaa57d498fca9cbaa79bbc72a4a4ffb4cf77a9c95d187eea8d059c2ecbae11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TACZA3OTAQQH4IEIKMVJWTULZO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hubert Soyer, Iain Dunning, Karen Simonyan, Koray Kavukcuoglu, Lasse Espeholt, Remi Munos, Shane Legg, Tim Harley, Tom Ward, Vlad Firoiu, Volodymir Mnih, Yotam Doron","submitted_at":"2018-02-05T18:47:30Z","abstract_excerpt":"In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters. A key challenge is to handle the increased amount of data and extended training time. We have developed a new distributed agent IMPALA (Importance Weighted Actor-Learner Architecture) that not only uses resources more efficiently in single-machine training but also scales to thousands of machines without sacrificing data efficiency or resource utilisation. We achieve stable learning at high throughput by combining decoupled acting and learning with a novel off-p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.01561","kind":"arxiv","version":3},"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":"2026-05-18T00:12:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CNdP3B1yS+Cf2wzpK7xAh8ZKjfjEq310WGnqtRTnYvtCKTz4EW5vJqKbHRiHvt/KSWHANIEGgqlEtmn+fgNpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T06:39:03.313462Z"},"content_sha256":"131023fd6fb92ac9af4ef2181d626d7c104932410b689caf2a69c6b19fecdb60","schema_version":"1.0","event_id":"sha256:131023fd6fb92ac9af4ef2181d626d7c104932410b689caf2a69c6b19fecdb60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TACZA3OTAQQH4IEIKMVJWTULZO/bundle.json","state_url":"https://pith.science/pith/TACZA3OTAQQH4IEIKMVJWTULZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TACZA3OTAQQH4IEIKMVJWTULZO/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":"2026-06-05T06:39:03Z","links":{"resolver":"https://pith.science/pith/TACZA3OTAQQH4IEIKMVJWTULZO","bundle":"https://pith.science/pith/TACZA3OTAQQH4IEIKMVJWTULZO/bundle.json","state":"https://pith.science/pith/TACZA3OTAQQH4IEIKMVJWTULZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TACZA3OTAQQH4IEIKMVJWTULZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TACZA3OTAQQH4IEIKMVJWTULZO","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":"7b982bad01d2e7d57b89bc0b15d6d44fb13ead0c0063d32b234bd66874ce9dcd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-05T18:47:30Z","title_canon_sha256":"457206bb96b574c4b1e16cb6477dead4082216e4e4788a9f3cc85b110a2aad07"},"schema_version":"1.0","source":{"id":"1802.01561","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.01561","created_at":"2026-05-18T00:12:08Z"},{"alias_kind":"arxiv_version","alias_value":"1802.01561v3","created_at":"2026-05-18T00:12:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.01561","created_at":"2026-05-18T00:12:08Z"},{"alias_kind":"pith_short_12","alias_value":"TACZA3OTAQQH","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TACZA3OTAQQH4IEI","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TACZA3OT","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:131023fd6fb92ac9af4ef2181d626d7c104932410b689caf2a69c6b19fecdb60","target":"graph","created_at":"2026-05-18T00:12:08Z","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":"In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters. A key challenge is to handle the increased amount of data and extended training time. We have developed a new distributed agent IMPALA (Importance Weighted Actor-Learner Architecture) that not only uses resources more efficiently in single-machine training but also scales to thousands of machines without sacrificing data efficiency or resource utilisation. We achieve stable learning at high throughput by combining decoupled acting and learning with a novel off-p","authors_text":"Hubert Soyer, Iain Dunning, Karen Simonyan, Koray Kavukcuoglu, Lasse Espeholt, Remi Munos, Shane Legg, Tim Harley, Tom Ward, Vlad Firoiu, Volodymir Mnih, Yotam Doron","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-05T18:47:30Z","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.01561","kind":"arxiv","version":3},"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:eccaa57d498fca9cbaa79bbc72a4a4ffb4cf77a9c95d187eea8d059c2ecbae11","target":"record","created_at":"2026-05-18T00:12:08Z","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":"7b982bad01d2e7d57b89bc0b15d6d44fb13ead0c0063d32b234bd66874ce9dcd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-05T18:47:30Z","title_canon_sha256":"457206bb96b574c4b1e16cb6477dead4082216e4e4788a9f3cc85b110a2aad07"},"schema_version":"1.0","source":{"id":"1802.01561","kind":"arxiv","version":3}},"canonical_sha256":"9805906dd304207e2088532a9b4e8bcbb762c038e0bd961cb7b7a21ecc74b0bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9805906dd304207e2088532a9b4e8bcbb762c038e0bd961cb7b7a21ecc74b0bd","first_computed_at":"2026-05-18T00:12:08.949103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:08.949103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t18uvJqTEUJCIA+8RP95CuoTRrBz5Aca7Wx3dxVsDJxhZue2/7GdggS4UuAxp/fj8TICgGcijD34cVjIOr5IAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:08.949583Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.01561","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eccaa57d498fca9cbaa79bbc72a4a4ffb4cf77a9c95d187eea8d059c2ecbae11","sha256:131023fd6fb92ac9af4ef2181d626d7c104932410b689caf2a69c6b19fecdb60"],"state_sha256":"0677961381beb1b5d4650ca041e0f1c0798a254a6d62f404e5b954989ecfe214"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aI7J5u4rZwS2F/UPAbZ6VkaCibpdhY0XMWSq1VdD14wAz/VSLEfzoX6S0D0zwWsgE1R8yyOwdtHkUQ7Nxe5FDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T06:39:03.316146Z","bundle_sha256":"ffd43331be819904e8d59073882ce2f1d151bb258b3887a61001bb8af6683ca1"}}