{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CGT4MQZA2QP5KCC3G25ZL3TG2T","short_pith_number":"pith:CGT4MQZA","schema_version":"1.0","canonical_sha256":"11a7c64320d41fd5085b36bb95ee66d4c87fb745dccd7409ea15f7528707eb88","source":{"kind":"arxiv","id":"1810.05762","version":2},"attestation_state":"computed","paper":{"title":"GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ankur Handa, Dieter Fox, Jacky Liang, Miles Macklin, Nuttapong Chentanez, Viktor Makoviychuk","submitted_at":"2018-10-12T23:48:09Z","abstract_excerpt":"Most Deep Reinforcement Learning (Deep RL) algorithms require a prohibitively large number of training samples for learning complex tasks. Many recent works on speeding up Deep RL have focused on distributed training and simulation. While distributed training is often done on the GPU, simulation is not. In this work, we propose using GPU-accelerated RL simulations as an alternative to CPU ones. Using NVIDIA Flex, a GPU-based physics engine, we show promising speed-ups of learning various continuous-control, locomotion tasks. With one GPU and CPU core, we are able to train the Humanoid running "},"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":"1810.05762","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-10-12T23:48:09Z","cross_cats_sorted":[],"title_canon_sha256":"99974912b39c93d62ea6f510e07214628408608f97dbde0e63ebd4b49ab6a652","abstract_canon_sha256":"a2e22d2eed588259ed2aedaf9678e082f8758e4c908c8236126be495f95a955b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:24.601937Z","signature_b64":"LZ+jqFGkYawcFpCGWs0XncL6i6vdZxre1leecxq1PBJTVkHmaA8UbPVN+UrGV5Yj8WrB0BUP10zUwDEAB4Q+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11a7c64320d41fd5085b36bb95ee66d4c87fb745dccd7409ea15f7528707eb88","last_reissued_at":"2026-05-18T00:02:24.601263Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:24.601263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ankur Handa, Dieter Fox, Jacky Liang, Miles Macklin, Nuttapong Chentanez, Viktor Makoviychuk","submitted_at":"2018-10-12T23:48:09Z","abstract_excerpt":"Most Deep Reinforcement Learning (Deep RL) algorithms require a prohibitively large number of training samples for learning complex tasks. Many recent works on speeding up Deep RL have focused on distributed training and simulation. While distributed training is often done on the GPU, simulation is not. In this work, we propose using GPU-accelerated RL simulations as an alternative to CPU ones. Using NVIDIA Flex, a GPU-based physics engine, we show promising speed-ups of learning various continuous-control, locomotion tasks. With one GPU and CPU core, we are able to train the Humanoid running "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05762","kind":"arxiv","version":2},"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":"1810.05762","created_at":"2026-05-18T00:02:24.601353+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.05762v2","created_at":"2026-05-18T00:02:24.601353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05762","created_at":"2026-05-18T00:02:24.601353+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGT4MQZA2QP5","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGT4MQZA2QP5KCC3","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGT4MQZA","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16395","citing_title":"OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGT4MQZA2QP5KCC3G25ZL3TG2T","json":"https://pith.science/pith/CGT4MQZA2QP5KCC3G25ZL3TG2T.json","graph_json":"https://pith.science/api/pith-number/CGT4MQZA2QP5KCC3G25ZL3TG2T/graph.json","events_json":"https://pith.science/api/pith-number/CGT4MQZA2QP5KCC3G25ZL3TG2T/events.json","paper":"https://pith.science/paper/CGT4MQZA"},"agent_actions":{"view_html":"https://pith.science/pith/CGT4MQZA2QP5KCC3G25ZL3TG2T","download_json":"https://pith.science/pith/CGT4MQZA2QP5KCC3G25ZL3TG2T.json","view_paper":"https://pith.science/paper/CGT4MQZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.05762&json=true","fetch_graph":"https://pith.science/api/pith-number/CGT4MQZA2QP5KCC3G25ZL3TG2T/graph.json","fetch_events":"https://pith.science/api/pith-number/CGT4MQZA2QP5KCC3G25ZL3TG2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGT4MQZA2QP5KCC3G25ZL3TG2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGT4MQZA2QP5KCC3G25ZL3TG2T/action/storage_attestation","attest_author":"https://pith.science/pith/CGT4MQZA2QP5KCC3G25ZL3TG2T/action/author_attestation","sign_citation":"https://pith.science/pith/CGT4MQZA2QP5KCC3G25ZL3TG2T/action/citation_signature","submit_replication":"https://pith.science/pith/CGT4MQZA2QP5KCC3G25ZL3TG2T/action/replication_record"}},"created_at":"2026-05-18T00:02:24.601353+00:00","updated_at":"2026-05-18T00:02:24.601353+00:00"}