{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ASZXOHP5AKY5KZTPHO6GAKJOHG","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":"cdb243f859b86cb3630870c0ff7ae7191c84601fa625109124e05cf4160c4788","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-07T18:39:12Z","title_canon_sha256":"9f5bc62d3bc7ef0e564f882a65c53c62e2684d07aa9e986d4e213f92b3107c08"},"schema_version":"1.0","source":{"id":"1803.02811","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.02811","created_at":"2026-05-17T23:56:34Z"},{"alias_kind":"arxiv_version","alias_value":"1803.02811v2","created_at":"2026-05-17T23:56:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02811","created_at":"2026-05-17T23:56:34Z"},{"alias_kind":"pith_short_12","alias_value":"ASZXOHP5AKY5","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ASZXOHP5AKY5KZTP","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ASZXOHP5","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:381766b76f4f0511f23b7e55d7fbcadd7771ce011e3093a92d60c923e6bb5e18","target":"graph","created_at":"2026-05-17T23:56:34Z","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":"Deep reinforcement learning (RL) has achieved many recent successes, yet experiment turn-around time remains a key bottleneck in research and in practice. We investigate how to optimize existing deep RL algorithms for modern computers, specifically for a combination of CPUs and GPUs. We confirm that both policy gradient and Q-value learning algorithms can be adapted to learn using many parallel simulator instances. We further find it possible to train using batch sizes considerably larger than are standard, without negatively affecting sample complexity or final performance. We leverage these ","authors_text":"Adam Stooke, Pieter Abbeel","cross_cats":["cs.AI","cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-07T18:39:12Z","title":"Accelerated Methods for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.02811","kind":"arxiv","version":2},"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:a5d802a0834680acbe8dde4d4a56945c24c8af797099976c0a5ab21f81dcb0e5","target":"record","created_at":"2026-05-17T23:56:34Z","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":"cdb243f859b86cb3630870c0ff7ae7191c84601fa625109124e05cf4160c4788","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-07T18:39:12Z","title_canon_sha256":"9f5bc62d3bc7ef0e564f882a65c53c62e2684d07aa9e986d4e213f92b3107c08"},"schema_version":"1.0","source":{"id":"1803.02811","kind":"arxiv","version":2}},"canonical_sha256":"04b3771dfd02b1d5666f3bbc60292e39ae31509555cabd7dc5636b4f04fc110d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04b3771dfd02b1d5666f3bbc60292e39ae31509555cabd7dc5636b4f04fc110d","first_computed_at":"2026-05-17T23:56:34.113539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:34.113539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q/k5ya+AbG3+vthviV4mlw8rfqUZTrM7B2xfb0cU0vpVYAvvRuoUUI/NmyKwT7bDI/WClNHx0aeg2PEoxES7Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:34.114275Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.02811","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5d802a0834680acbe8dde4d4a56945c24c8af797099976c0a5ab21f81dcb0e5","sha256:381766b76f4f0511f23b7e55d7fbcadd7771ce011e3093a92d60c923e6bb5e18"],"state_sha256":"a23484dad4e5243b7333781cba7d771be15e19c94b8454c2ac2fcd9e7be6dbf0"}