{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:R4GREV47H2JD2GI5NSX6ERZQKC","short_pith_number":"pith:R4GREV47","schema_version":"1.0","canonical_sha256":"8f0d12579f3e923d191d6cafe24730509b78b49183480118cbcc599b5e567b77","source":{"kind":"arxiv","id":"1711.10137","version":2},"attestation_state":"computed","paper":{"title":"One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Jake Bruce, Michael Milford, Niko Suenderhauf, Piotr Mirowski, Raia Hadsell","submitted_at":"2017-11-28T06:03:14Z","abstract_excerpt":"Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is that interaction with the real world is costly, but training on limited experience is prone to overfitting. We present a method for learning to navigate, to a fixed goal and in a known environment, on a mobile robot. The robot leverages an interactive world model built from a single traversal of the environment, a pre-trained visual feature encoder, and stoch"},"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":"1711.10137","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-28T06:03:14Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"390e843019804c83e743ce57b2819e938298f7f4be2335344f43e97418c8603e","abstract_canon_sha256":"253f348f3daa0eac3edcf9deec69093227c1c47c2add5dd841ca07c5d30510e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:17.837479Z","signature_b64":"6L84JW5RHQ3eza0lRKYFCuaf0yHYTW2TGkELkjSHlwve86PrGqtQQVVPzqqqC/VelnYcQYt5YNHXSstYbKuTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f0d12579f3e923d191d6cafe24730509b78b49183480118cbcc599b5e567b77","last_reissued_at":"2026-05-18T00:29:17.836775Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:17.836775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Jake Bruce, Michael Milford, Niko Suenderhauf, Piotr Mirowski, Raia Hadsell","submitted_at":"2017-11-28T06:03:14Z","abstract_excerpt":"Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is that interaction with the real world is costly, but training on limited experience is prone to overfitting. We present a method for learning to navigate, to a fixed goal and in a known environment, on a mobile robot. The robot leverages an interactive world model built from a single traversal of the environment, a pre-trained visual feature encoder, and stoch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10137","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":"1711.10137","created_at":"2026-05-18T00:29:17.836882+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.10137v2","created_at":"2026-05-18T00:29:17.836882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10137","created_at":"2026-05-18T00:29:17.836882+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4GREV47H2JD","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4GREV47H2JD2GI5","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4GREV47","created_at":"2026-05-18T12:31:39.905425+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/R4GREV47H2JD2GI5NSX6ERZQKC","json":"https://pith.science/pith/R4GREV47H2JD2GI5NSX6ERZQKC.json","graph_json":"https://pith.science/api/pith-number/R4GREV47H2JD2GI5NSX6ERZQKC/graph.json","events_json":"https://pith.science/api/pith-number/R4GREV47H2JD2GI5NSX6ERZQKC/events.json","paper":"https://pith.science/paper/R4GREV47"},"agent_actions":{"view_html":"https://pith.science/pith/R4GREV47H2JD2GI5NSX6ERZQKC","download_json":"https://pith.science/pith/R4GREV47H2JD2GI5NSX6ERZQKC.json","view_paper":"https://pith.science/paper/R4GREV47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.10137&json=true","fetch_graph":"https://pith.science/api/pith-number/R4GREV47H2JD2GI5NSX6ERZQKC/graph.json","fetch_events":"https://pith.science/api/pith-number/R4GREV47H2JD2GI5NSX6ERZQKC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4GREV47H2JD2GI5NSX6ERZQKC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4GREV47H2JD2GI5NSX6ERZQKC/action/storage_attestation","attest_author":"https://pith.science/pith/R4GREV47H2JD2GI5NSX6ERZQKC/action/author_attestation","sign_citation":"https://pith.science/pith/R4GREV47H2JD2GI5NSX6ERZQKC/action/citation_signature","submit_replication":"https://pith.science/pith/R4GREV47H2JD2GI5NSX6ERZQKC/action/replication_record"}},"created_at":"2026-05-18T00:29:17.836882+00:00","updated_at":"2026-05-18T00:29:17.836882+00:00"}