{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2DHGSTSVYIU6RI43U2N2P22NPO","short_pith_number":"pith:2DHGSTSV","schema_version":"1.0","canonical_sha256":"d0ce694e55c229e8a39ba69ba7eb4d7bbc14ac4eee7c4ea0977d528f45365e0d","source":{"kind":"arxiv","id":"1904.01806","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Wolf, Edward Beeching, Jilles Dibangoye, Olivier Simonin","submitted_at":"2019-04-03T07:15:46Z","abstract_excerpt":"An important goal of research in Deep Reinforcement Learning in mobile robotics is to train agents capable of solving complex tasks, which require a high level of scene understanding and reasoning from an egocentric perspective. When trained from simulations, optimal environments should satisfy a currently unobtainable combination of high-fidelity photographic observations, massive amounts of different environment configurations and fast simulation speeds. In this paper we argue that research on training agents capable of complex reasoning can be simplified by decoupling from the requirement o"},"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":"1904.01806","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-03T07:15:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a9eebc45772dfca5c74b11ab1dd0899e79faf4a4e556a97a23696769ea63b21d","abstract_canon_sha256":"d8adeef1432bef0c4fff3a3fd566286328d21194f5998dac62ee015408127a2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:29.614715Z","signature_b64":"VWJn58OzklCwH4ATamxv2wlFgTdfOjrszeW1yvUTp9a4Xh+yWQbrDM8K21lmlmIgM4ewz4fZNU/PdPqqrX4lCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0ce694e55c229e8a39ba69ba7eb4d7bbc14ac4eee7c4ea0977d528f45365e0d","last_reissued_at":"2026-05-17T23:49:29.614074Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:29.614074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Wolf, Edward Beeching, Jilles Dibangoye, Olivier Simonin","submitted_at":"2019-04-03T07:15:46Z","abstract_excerpt":"An important goal of research in Deep Reinforcement Learning in mobile robotics is to train agents capable of solving complex tasks, which require a high level of scene understanding and reasoning from an egocentric perspective. When trained from simulations, optimal environments should satisfy a currently unobtainable combination of high-fidelity photographic observations, massive amounts of different environment configurations and fast simulation speeds. In this paper we argue that research on training agents capable of complex reasoning can be simplified by decoupling from the requirement o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01806","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":"1904.01806","created_at":"2026-05-17T23:49:29.614174+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01806v1","created_at":"2026-05-17T23:49:29.614174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01806","created_at":"2026-05-17T23:49:29.614174+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DHGSTSVYIU6","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DHGSTSVYIU6RI43","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DHGSTSV","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DHGSTSVYIU6RI43U2N2P22NPO","json":"https://pith.science/pith/2DHGSTSVYIU6RI43U2N2P22NPO.json","graph_json":"https://pith.science/api/pith-number/2DHGSTSVYIU6RI43U2N2P22NPO/graph.json","events_json":"https://pith.science/api/pith-number/2DHGSTSVYIU6RI43U2N2P22NPO/events.json","paper":"https://pith.science/paper/2DHGSTSV"},"agent_actions":{"view_html":"https://pith.science/pith/2DHGSTSVYIU6RI43U2N2P22NPO","download_json":"https://pith.science/pith/2DHGSTSVYIU6RI43U2N2P22NPO.json","view_paper":"https://pith.science/paper/2DHGSTSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01806&json=true","fetch_graph":"https://pith.science/api/pith-number/2DHGSTSVYIU6RI43U2N2P22NPO/graph.json","fetch_events":"https://pith.science/api/pith-number/2DHGSTSVYIU6RI43U2N2P22NPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DHGSTSVYIU6RI43U2N2P22NPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DHGSTSVYIU6RI43U2N2P22NPO/action/storage_attestation","attest_author":"https://pith.science/pith/2DHGSTSVYIU6RI43U2N2P22NPO/action/author_attestation","sign_citation":"https://pith.science/pith/2DHGSTSVYIU6RI43U2N2P22NPO/action/citation_signature","submit_replication":"https://pith.science/pith/2DHGSTSVYIU6RI43U2N2P22NPO/action/replication_record"}},"created_at":"2026-05-17T23:49:29.614174+00:00","updated_at":"2026-05-17T23:49:29.614174+00:00"}