{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:67BWXEGXETAZWOA5EP645JJCIK","short_pith_number":"pith:67BWXEGX","schema_version":"1.0","canonical_sha256":"f7c36b90d724c19b381d23fdcea52242ba043882918d3225fc4d42d45adb96cb","source":{"kind":"arxiv","id":"1903.11774","version":1},"attestation_state":"computed","paper":{"title":"How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Su, Henrik I. Christensen, Quan Vuong, Sharad Vikram, Sicun Gao","submitted_at":"2019-03-28T03:24:44Z","abstract_excerpt":"Recently, reinforcement learning (RL) algorithms have demonstrated remarkable success in learning complicated behaviors from minimally processed input. However, most of this success is limited to simulation. While there are promising successes in applying RL algorithms directly on real systems, their performance on more complex systems remains bottle-necked by the relative data inefficiency of RL algorithms. Domain randomization is a promising direction of research that has demonstrated impressive results using RL algorithms to control real robots. At a high level, domain randomization works b"},"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":"1903.11774","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-28T03:24:44Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"91f2e0027e6f92f68f221e3c2a5888d8e7014ca948e32191f815ec869d280722","abstract_canon_sha256":"6e19a8a240e62a1128352acdd67abe7e37d45742b938386d614c9e6a24c169bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:01.829515Z","signature_b64":"PyeB3HblKr4tEW9mBxVHV6q4yZ7BrU1S+7POnw4JJifBEJQ1nCijIMBuTQuArbWH2HUSv8i8Yot4a54dNEOWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7c36b90d724c19b381d23fdcea52242ba043882918d3225fc4d42d45adb96cb","last_reissued_at":"2026-05-17T23:50:01.829060Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:01.829060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Su, Henrik I. Christensen, Quan Vuong, Sharad Vikram, Sicun Gao","submitted_at":"2019-03-28T03:24:44Z","abstract_excerpt":"Recently, reinforcement learning (RL) algorithms have demonstrated remarkable success in learning complicated behaviors from minimally processed input. However, most of this success is limited to simulation. While there are promising successes in applying RL algorithms directly on real systems, their performance on more complex systems remains bottle-necked by the relative data inefficiency of RL algorithms. Domain randomization is a promising direction of research that has demonstrated impressive results using RL algorithms to control real robots. At a high level, domain randomization works b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.11774","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1903.11774","created_at":"2026-05-17T23:50:01.829127+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.11774v1","created_at":"2026-05-17T23:50:01.829127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.11774","created_at":"2026-05-17T23:50:01.829127+00:00"},{"alias_kind":"pith_short_12","alias_value":"67BWXEGXETAZ","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"67BWXEGXETAZWOA5","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"67BWXEGX","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":115,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67BWXEGXETAZWOA5EP645JJCIK","json":"https://pith.science/pith/67BWXEGXETAZWOA5EP645JJCIK.json","graph_json":"https://pith.science/api/pith-number/67BWXEGXETAZWOA5EP645JJCIK/graph.json","events_json":"https://pith.science/api/pith-number/67BWXEGXETAZWOA5EP645JJCIK/events.json","paper":"https://pith.science/paper/67BWXEGX"},"agent_actions":{"view_html":"https://pith.science/pith/67BWXEGXETAZWOA5EP645JJCIK","download_json":"https://pith.science/pith/67BWXEGXETAZWOA5EP645JJCIK.json","view_paper":"https://pith.science/paper/67BWXEGX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.11774&json=true","fetch_graph":"https://pith.science/api/pith-number/67BWXEGXETAZWOA5EP645JJCIK/graph.json","fetch_events":"https://pith.science/api/pith-number/67BWXEGXETAZWOA5EP645JJCIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67BWXEGXETAZWOA5EP645JJCIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67BWXEGXETAZWOA5EP645JJCIK/action/storage_attestation","attest_author":"https://pith.science/pith/67BWXEGXETAZWOA5EP645JJCIK/action/author_attestation","sign_citation":"https://pith.science/pith/67BWXEGXETAZWOA5EP645JJCIK/action/citation_signature","submit_replication":"https://pith.science/pith/67BWXEGXETAZWOA5EP645JJCIK/action/replication_record"}},"created_at":"2026-05-17T23:50:01.829127+00:00","updated_at":"2026-05-17T23:50:01.829127+00:00"}