{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TWEKI633W5ZIXCKODH6FHVSVPU","short_pith_number":"pith:TWEKI633","schema_version":"1.0","canonical_sha256":"9d88a47b7bb7728b894e19fc53d6557d0baa75dc0d6a08d03f01885e8c787e98","source":{"kind":"arxiv","id":"1803.01846","version":1},"attestation_state":"computed","paper":{"title":"Learning Sample-Efficient Target Reaching for Mobile Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alejandro Ribeiro, Arbaaz Khan, Vijay Kumar","submitted_at":"2018-03-05T03:45:53Z","abstract_excerpt":"In this paper, we propose a novel architecture and a self-supervised policy gradient algorithm, which employs unsupervised auxiliary tasks to enable a mobile robot to learn how to navigate to a given goal. The dependency on the global information is eliminated by providing only sparse range-finder measurements to the robot. The partially observable planning problem is addressed by splitting it into a hierarchical process. We use convolutional networks to plan locally, and a differentiable memory to provide information about past time steps in the trajectory. These modules, combined in our netw"},"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":"1803.01846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-05T03:45:53Z","cross_cats_sorted":[],"title_canon_sha256":"1e327975aae6006167b4d89f1df158761ca2e208a03c8c1a6979ad352a7b8160","abstract_canon_sha256":"33ccc242535de7824314f151a5eed148e56699f07db649a7e45113875fa318b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:56.465399Z","signature_b64":"jVUz59KTGqGJOmPM2Mf7Ut0Fx+rpCF5L5BNXwN89cI2wWJwFpmrt5D6M3IQOY5k2pWq5ccgyG67ewgI5SKQdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d88a47b7bb7728b894e19fc53d6557d0baa75dc0d6a08d03f01885e8c787e98","last_reissued_at":"2026-05-18T00:21:56.464862Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:56.464862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Sample-Efficient Target Reaching for Mobile Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alejandro Ribeiro, Arbaaz Khan, Vijay Kumar","submitted_at":"2018-03-05T03:45:53Z","abstract_excerpt":"In this paper, we propose a novel architecture and a self-supervised policy gradient algorithm, which employs unsupervised auxiliary tasks to enable a mobile robot to learn how to navigate to a given goal. The dependency on the global information is eliminated by providing only sparse range-finder measurements to the robot. The partially observable planning problem is addressed by splitting it into a hierarchical process. We use convolutional networks to plan locally, and a differentiable memory to provide information about past time steps in the trajectory. These modules, combined in our netw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01846","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":"1803.01846","created_at":"2026-05-18T00:21:56.464934+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.01846v1","created_at":"2026-05-18T00:21:56.464934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01846","created_at":"2026-05-18T00:21:56.464934+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWEKI633W5ZI","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWEKI633W5ZIXCKO","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWEKI633","created_at":"2026-05-18T12:32:56.356000+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/TWEKI633W5ZIXCKODH6FHVSVPU","json":"https://pith.science/pith/TWEKI633W5ZIXCKODH6FHVSVPU.json","graph_json":"https://pith.science/api/pith-number/TWEKI633W5ZIXCKODH6FHVSVPU/graph.json","events_json":"https://pith.science/api/pith-number/TWEKI633W5ZIXCKODH6FHVSVPU/events.json","paper":"https://pith.science/paper/TWEKI633"},"agent_actions":{"view_html":"https://pith.science/pith/TWEKI633W5ZIXCKODH6FHVSVPU","download_json":"https://pith.science/pith/TWEKI633W5ZIXCKODH6FHVSVPU.json","view_paper":"https://pith.science/paper/TWEKI633","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.01846&json=true","fetch_graph":"https://pith.science/api/pith-number/TWEKI633W5ZIXCKODH6FHVSVPU/graph.json","fetch_events":"https://pith.science/api/pith-number/TWEKI633W5ZIXCKODH6FHVSVPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWEKI633W5ZIXCKODH6FHVSVPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWEKI633W5ZIXCKODH6FHVSVPU/action/storage_attestation","attest_author":"https://pith.science/pith/TWEKI633W5ZIXCKODH6FHVSVPU/action/author_attestation","sign_citation":"https://pith.science/pith/TWEKI633W5ZIXCKODH6FHVSVPU/action/citation_signature","submit_replication":"https://pith.science/pith/TWEKI633W5ZIXCKODH6FHVSVPU/action/replication_record"}},"created_at":"2026-05-18T00:21:56.464934+00:00","updated_at":"2026-05-18T00:21:56.464934+00:00"}