{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Q2TGAGGD5FSULR2RIZKQLJ6KUX","short_pith_number":"pith:Q2TGAGGD","schema_version":"1.0","canonical_sha256":"86a66018c3e96545c751465505a7caa5e648a23fe40a96428ba7c1165297cdc8","source":{"kind":"arxiv","id":"2007.14545","version":2},"attestation_state":"computed","paper":{"title":"Learning Object-conditioned Exploration using Distributed Soft Actor Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alexander Toshev, Austin Stone, Ayzaan Wahid, Brian Ichter, Kevin Chen","submitted_at":"2020-07-29T01:09:27Z","abstract_excerpt":"Object navigation is defined as navigating to an object of a given label in a complex, unexplored environment. In its general form, this problem poses several challenges for Robotics: semantic exploration of unknown environments in search of an object and low-level control. In this work we study object-guided exploration and low-level control, and present an end-to-end trained navigation policy achieving a success rate of 0.68 and SPL of 0.58 on unseen, visually complex scans of real homes. We propose a highly scalable implementation of an off-policy Reinforcement Learning algorithm, distribut"},"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":"2007.14545","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-07-29T01:09:27Z","cross_cats_sorted":[],"title_canon_sha256":"200408ac86613f06391cc87ae514bcb001beaca2ed67300d056f1a05afe43e99","abstract_canon_sha256":"83ef5a39e5949a40a0753e7370e18bac647e71474a9b1989da45a14208610c07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:26.233140Z","signature_b64":"vMdQ6lipgzsBldyh5lhTDRCD/ilbOi+JcO4wrbIAMlDAaE3RL7AHoKxL9ReAHpNpSh7FORUOPus33iFqxOqkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86a66018c3e96545c751465505a7caa5e648a23fe40a96428ba7c1165297cdc8","last_reissued_at":"2026-07-05T01:23:26.232621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:26.232621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Object-conditioned Exploration using Distributed Soft Actor Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alexander Toshev, Austin Stone, Ayzaan Wahid, Brian Ichter, Kevin Chen","submitted_at":"2020-07-29T01:09:27Z","abstract_excerpt":"Object navigation is defined as navigating to an object of a given label in a complex, unexplored environment. In its general form, this problem poses several challenges for Robotics: semantic exploration of unknown environments in search of an object and low-level control. In this work we study object-guided exploration and low-level control, and present an end-to-end trained navigation policy achieving a success rate of 0.68 and SPL of 0.58 on unseen, visually complex scans of real homes. We propose a highly scalable implementation of an off-policy Reinforcement Learning algorithm, distribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.14545","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/2007.14545/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":"2007.14545","created_at":"2026-07-05T01:23:26.232683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.14545v2","created_at":"2026-07-05T01:23:26.232683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.14545","created_at":"2026-07-05T01:23:26.232683+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2TGAGGD5FSU","created_at":"2026-07-05T01:23:26.232683+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2TGAGGD5FSULR2R","created_at":"2026-07-05T01:23:26.232683+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2TGAGGD","created_at":"2026-07-05T01:23:26.232683+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/Q2TGAGGD5FSULR2RIZKQLJ6KUX","json":"https://pith.science/pith/Q2TGAGGD5FSULR2RIZKQLJ6KUX.json","graph_json":"https://pith.science/api/pith-number/Q2TGAGGD5FSULR2RIZKQLJ6KUX/graph.json","events_json":"https://pith.science/api/pith-number/Q2TGAGGD5FSULR2RIZKQLJ6KUX/events.json","paper":"https://pith.science/paper/Q2TGAGGD"},"agent_actions":{"view_html":"https://pith.science/pith/Q2TGAGGD5FSULR2RIZKQLJ6KUX","download_json":"https://pith.science/pith/Q2TGAGGD5FSULR2RIZKQLJ6KUX.json","view_paper":"https://pith.science/paper/Q2TGAGGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.14545&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2TGAGGD5FSULR2RIZKQLJ6KUX/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2TGAGGD5FSULR2RIZKQLJ6KUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2TGAGGD5FSULR2RIZKQLJ6KUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2TGAGGD5FSULR2RIZKQLJ6KUX/action/storage_attestation","attest_author":"https://pith.science/pith/Q2TGAGGD5FSULR2RIZKQLJ6KUX/action/author_attestation","sign_citation":"https://pith.science/pith/Q2TGAGGD5FSULR2RIZKQLJ6KUX/action/citation_signature","submit_replication":"https://pith.science/pith/Q2TGAGGD5FSULR2RIZKQLJ6KUX/action/replication_record"}},"created_at":"2026-07-05T01:23:26.232683+00:00","updated_at":"2026-07-05T01:23:26.232683+00:00"}