{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2E76JRF3LPPJHPOMU7VINAEK5O","short_pith_number":"pith:2E76JRF3","schema_version":"1.0","canonical_sha256":"d13fe4c4bb5bde93bdcca7ea86808aeba9b4f7f514a6f1b963789194859a49ee","source":{"kind":"arxiv","id":"1904.04762","version":2},"attestation_state":"computed","paper":{"title":"Active Domain Randomization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bhairav Mehta, Christopher J. Pal, Florian Golemo, Liam Paull, Manfred Diaz","submitted_at":"2019-04-09T16:15:39Z","abstract_excerpt":"Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is unknown or cannot easily be used for training. In this work, we empirically examine the effects of domain randomization on agent generalization. Our experiments show that domain randomization may lead to suboptimal, high-variance policies, which we attribute to the uniform sampling of environment parameters. We propose Active Domain Randomization, a novel algorithm that learns a parameter sampling strategy. Our method looks for the most informative environment "},"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":"1904.04762","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-09T16:15:39Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"10bd4db6afe3f5a8e064cee827d760f2bb2d2d011a7ffe2edd56fd88a9574714","abstract_canon_sha256":"f0947e0715d44824a117b9fca2414aaead3c7b98517d38d15da29a0ce61a9551"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:55.229311Z","signature_b64":"hcCDYluCyyESitfEip4D3Jn6G/wSkGEY7sSESF5UQ9MSwFw90FsmGrORNZ20regNiz6WBakC6vx6xzhXs3MXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d13fe4c4bb5bde93bdcca7ea86808aeba9b4f7f514a6f1b963789194859a49ee","last_reissued_at":"2026-05-17T23:40:55.228694Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:55.228694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Domain Randomization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bhairav Mehta, Christopher J. Pal, Florian Golemo, Liam Paull, Manfred Diaz","submitted_at":"2019-04-09T16:15:39Z","abstract_excerpt":"Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is unknown or cannot easily be used for training. In this work, we empirically examine the effects of domain randomization on agent generalization. Our experiments show that domain randomization may lead to suboptimal, high-variance policies, which we attribute to the uniform sampling of environment parameters. We propose Active Domain Randomization, a novel algorithm that learns a parameter sampling strategy. Our method looks for the most informative environment "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04762","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":"1904.04762","created_at":"2026-05-17T23:40:55.228795+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.04762v2","created_at":"2026-05-17T23:40:55.228795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04762","created_at":"2026-05-17T23:40:55.228795+00:00"},{"alias_kind":"pith_short_12","alias_value":"2E76JRF3LPPJ","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2E76JRF3LPPJHPOM","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2E76JRF3","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":223,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2E76JRF3LPPJHPOMU7VINAEK5O","json":"https://pith.science/pith/2E76JRF3LPPJHPOMU7VINAEK5O.json","graph_json":"https://pith.science/api/pith-number/2E76JRF3LPPJHPOMU7VINAEK5O/graph.json","events_json":"https://pith.science/api/pith-number/2E76JRF3LPPJHPOMU7VINAEK5O/events.json","paper":"https://pith.science/paper/2E76JRF3"},"agent_actions":{"view_html":"https://pith.science/pith/2E76JRF3LPPJHPOMU7VINAEK5O","download_json":"https://pith.science/pith/2E76JRF3LPPJHPOMU7VINAEK5O.json","view_paper":"https://pith.science/paper/2E76JRF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.04762&json=true","fetch_graph":"https://pith.science/api/pith-number/2E76JRF3LPPJHPOMU7VINAEK5O/graph.json","fetch_events":"https://pith.science/api/pith-number/2E76JRF3LPPJHPOMU7VINAEK5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2E76JRF3LPPJHPOMU7VINAEK5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2E76JRF3LPPJHPOMU7VINAEK5O/action/storage_attestation","attest_author":"https://pith.science/pith/2E76JRF3LPPJHPOMU7VINAEK5O/action/author_attestation","sign_citation":"https://pith.science/pith/2E76JRF3LPPJHPOMU7VINAEK5O/action/citation_signature","submit_replication":"https://pith.science/pith/2E76JRF3LPPJHPOMU7VINAEK5O/action/replication_record"}},"created_at":"2026-05-17T23:40:55.228795+00:00","updated_at":"2026-05-17T23:40:55.228795+00:00"}