{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HTTK4U5PHQD53UBDCCCXCDGPUJ","short_pith_number":"pith:HTTK4U5P","schema_version":"1.0","canonical_sha256":"3ce6ae53af3c07ddd0231085710ccfa25ff234c2b681e8e2975dbf67a9be7035","source":{"kind":"arxiv","id":"1905.09275","version":2},"attestation_state":"computed","paper":{"title":"COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Lerchner, Christopher P. Burgess, Loic Matthey, Matko Bosnjak, Nicholas Watters","submitted_at":"2019-05-22T17:59:32Z","abstract_excerpt":"Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms. Here we introduce a modular approach to addressing these challenges in a continuous control environment, without using hand-crafted or supervised information. Our Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of its environment and action space. Subsequently, it can learn a variety of tasks through model-based search in very few steps and excel on structured "},"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":"1905.09275","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-22T17:59:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14944928ca77353aee0c35a1b14f64a531a2bea9ea78f8677737dd8b3cd0e19c","abstract_canon_sha256":"5b6ab6b5b51c5c02502a5a88fa283b256a701fcbde45aaf744045da18b518a2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:55:55.889123Z","signature_b64":"qRWJ+aK8WAqWktMoCifo82x1W38OAYuJDuYoIaZyJOJtCc16jFH8+o+qIxCTJhKxqS0CUR78wi3FwdLGv7JcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ce6ae53af3c07ddd0231085710ccfa25ff234c2b681e8e2975dbf67a9be7035","last_reissued_at":"2026-07-04T23:55:55.888730Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:55:55.888730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Lerchner, Christopher P. Burgess, Loic Matthey, Matko Bosnjak, Nicholas Watters","submitted_at":"2019-05-22T17:59:32Z","abstract_excerpt":"Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms. Here we introduce a modular approach to addressing these challenges in a continuous control environment, without using hand-crafted or supervised information. Our Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of its environment and action space. Subsequently, it can learn a variety of tasks through model-based search in very few steps and excel on structured "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09275","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.09275/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":"1905.09275","created_at":"2026-07-04T23:55:55.888788+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09275v2","created_at":"2026-07-04T23:55:55.888788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09275","created_at":"2026-07-04T23:55:55.888788+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTTK4U5PHQD5","created_at":"2026-07-04T23:55:55.888788+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTTK4U5PHQD53UBD","created_at":"2026-07-04T23:55:55.888788+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTTK4U5P","created_at":"2026-07-04T23:55:55.888788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16054","citing_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","ref_index":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTTK4U5PHQD53UBDCCCXCDGPUJ","json":"https://pith.science/pith/HTTK4U5PHQD53UBDCCCXCDGPUJ.json","graph_json":"https://pith.science/api/pith-number/HTTK4U5PHQD53UBDCCCXCDGPUJ/graph.json","events_json":"https://pith.science/api/pith-number/HTTK4U5PHQD53UBDCCCXCDGPUJ/events.json","paper":"https://pith.science/paper/HTTK4U5P"},"agent_actions":{"view_html":"https://pith.science/pith/HTTK4U5PHQD53UBDCCCXCDGPUJ","download_json":"https://pith.science/pith/HTTK4U5PHQD53UBDCCCXCDGPUJ.json","view_paper":"https://pith.science/paper/HTTK4U5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09275&json=true","fetch_graph":"https://pith.science/api/pith-number/HTTK4U5PHQD53UBDCCCXCDGPUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HTTK4U5PHQD53UBDCCCXCDGPUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTTK4U5PHQD53UBDCCCXCDGPUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTTK4U5PHQD53UBDCCCXCDGPUJ/action/storage_attestation","attest_author":"https://pith.science/pith/HTTK4U5PHQD53UBDCCCXCDGPUJ/action/author_attestation","sign_citation":"https://pith.science/pith/HTTK4U5PHQD53UBDCCCXCDGPUJ/action/citation_signature","submit_replication":"https://pith.science/pith/HTTK4U5PHQD53UBDCCCXCDGPUJ/action/replication_record"}},"created_at":"2026-07-04T23:55:55.888788+00:00","updated_at":"2026-07-04T23:55:55.888788+00:00"}