{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YK4HF7U3KUKBILZ5CV6MTALTMO","short_pith_number":"pith:YK4HF7U3","schema_version":"1.0","canonical_sha256":"c2b872fe9b5514142f3d157cc9817363b66db8a9615a56bd3c58aeaf268455bb","source":{"kind":"arxiv","id":"2103.07013","version":1},"attestation_state":"computed","paper":{"title":"Large Batch Simulation for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.GR"],"primary_cat":"cs.LG","authors_text":"Aleksei Petrenko, Brennan Shacklett, Dhruv Batra, Erik Wijmans, Kayvon Fatahalian, Manolis Savva, Vladlen Koltun","submitted_at":"2021-03-12T00:22:50Z","abstract_excerpt":"We accelerate deep reinforcement learning-based training in visually complex 3D environments by two orders of magnitude over prior work, realizing end-to-end training speeds of over 19,000 frames of experience per second on a single GPU and up to 72,000 frames per second on a single eight-GPU machine. The key idea of our approach is to design a 3D renderer and embodied navigation simulator around the principle of \"batch simulation\": accepting and executing large batches of requests simultaneously. Beyond exposing large amounts of work at once, batch simulation allows implementations to amortiz"},"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":"2103.07013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-12T00:22:50Z","cross_cats_sorted":["cs.AI","cs.CV","cs.GR"],"title_canon_sha256":"3be500e473da9a00041c808a5b925ceccc110196d96ce3e89f459f00d296536f","abstract_canon_sha256":"0f8de36279cd5f9d2c15a15e275e809b366c5d02a08b4ec4ca6fef796094a8d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:27.657038Z","signature_b64":"uuaLp7bjWwaDKKXVOJgqknnTWAHMyDDtRB+zC+/+2Sb6/8WC7KTcP+6YCZR1/KQsKxC8Cb5sjQq+V/buXnp0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2b872fe9b5514142f3d157cc9817363b66db8a9615a56bd3c58aeaf268455bb","last_reissued_at":"2026-07-05T02:22:27.656637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:27.656637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Batch Simulation for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.GR"],"primary_cat":"cs.LG","authors_text":"Aleksei Petrenko, Brennan Shacklett, Dhruv Batra, Erik Wijmans, Kayvon Fatahalian, Manolis Savva, Vladlen Koltun","submitted_at":"2021-03-12T00:22:50Z","abstract_excerpt":"We accelerate deep reinforcement learning-based training in visually complex 3D environments by two orders of magnitude over prior work, realizing end-to-end training speeds of over 19,000 frames of experience per second on a single GPU and up to 72,000 frames per second on a single eight-GPU machine. The key idea of our approach is to design a 3D renderer and embodied navigation simulator around the principle of \"batch simulation\": accepting and executing large batches of requests simultaneously. Beyond exposing large amounts of work at once, batch simulation allows implementations to amortiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.07013","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.07013/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2103.07013","created_at":"2026-07-05T02:22:27.656695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.07013v1","created_at":"2026-07-05T02:22:27.656695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.07013","created_at":"2026-07-05T02:22:27.656695+00:00"},{"alias_kind":"pith_short_12","alias_value":"YK4HF7U3KUKB","created_at":"2026-07-05T02:22:27.656695+00:00"},{"alias_kind":"pith_short_16","alias_value":"YK4HF7U3KUKBILZ5","created_at":"2026-07-05T02:22:27.656695+00:00"},{"alias_kind":"pith_short_8","alias_value":"YK4HF7U3","created_at":"2026-07-05T02:22:27.656695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26833","citing_title":"Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YK4HF7U3KUKBILZ5CV6MTALTMO","json":"https://pith.science/pith/YK4HF7U3KUKBILZ5CV6MTALTMO.json","graph_json":"https://pith.science/api/pith-number/YK4HF7U3KUKBILZ5CV6MTALTMO/graph.json","events_json":"https://pith.science/api/pith-number/YK4HF7U3KUKBILZ5CV6MTALTMO/events.json","paper":"https://pith.science/paper/YK4HF7U3"},"agent_actions":{"view_html":"https://pith.science/pith/YK4HF7U3KUKBILZ5CV6MTALTMO","download_json":"https://pith.science/pith/YK4HF7U3KUKBILZ5CV6MTALTMO.json","view_paper":"https://pith.science/paper/YK4HF7U3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.07013&json=true","fetch_graph":"https://pith.science/api/pith-number/YK4HF7U3KUKBILZ5CV6MTALTMO/graph.json","fetch_events":"https://pith.science/api/pith-number/YK4HF7U3KUKBILZ5CV6MTALTMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YK4HF7U3KUKBILZ5CV6MTALTMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YK4HF7U3KUKBILZ5CV6MTALTMO/action/storage_attestation","attest_author":"https://pith.science/pith/YK4HF7U3KUKBILZ5CV6MTALTMO/action/author_attestation","sign_citation":"https://pith.science/pith/YK4HF7U3KUKBILZ5CV6MTALTMO/action/citation_signature","submit_replication":"https://pith.science/pith/YK4HF7U3KUKBILZ5CV6MTALTMO/action/replication_record"}},"created_at":"2026-07-05T02:22:27.656695+00:00","updated_at":"2026-07-05T02:22:27.656695+00:00"}