{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:27FP4AMJTMVFNBK2CAOB7RBUS2","short_pith_number":"pith:27FP4AMJ","schema_version":"1.0","canonical_sha256":"d7cafe01899b2a56855a101c1fc434968eaef22da1930dfd3362aa599b9e1618","source":{"kind":"arxiv","id":"2412.12024","version":1},"attestation_state":"computed","paper":{"title":"Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Lawson L.S. Wong, Linfeng Zhao","submitted_at":"2024-12-16T17:51:09Z","abstract_excerpt":"Learning navigation capabilities in different environments has long been one of the major challenges in decision-making. In this work, we focus on zero-shot navigation ability using given abstract $2$-D top-down maps. Like human navigation by reading a paper map, the agent reads the map as an image when navigating in a novel layout, after learning to navigate on a set of training maps. We propose a model-based reinforcement learning approach for this multi-task learning problem, where it jointly learns a hypermodel that takes top-down maps as input and predicts the weights of the transition ne"},"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":"2412.12024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T17:51:09Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"171a11e66c4fa9b8a8d12d1383119950ad3f75a6a74eddd61fc58337f4ac2602","abstract_canon_sha256":"5616f04fe4ea2b9639cd3f057babf493ff213f77c68826c06a92e1b2009f5c7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:55.586505Z","signature_b64":"FHfo+8/1sL9cCRVB2UJpRGzjQs3idGdT8tX84L8TGEk1DBqnTjKierB0kDZXCwH/9Rh4sFPRxjDKo3IDATItAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7cafe01899b2a56855a101c1fc434968eaef22da1930dfd3362aa599b9e1618","last_reissued_at":"2026-07-05T09:49:55.585970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:55.585970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Lawson L.S. Wong, Linfeng Zhao","submitted_at":"2024-12-16T17:51:09Z","abstract_excerpt":"Learning navigation capabilities in different environments has long been one of the major challenges in decision-making. In this work, we focus on zero-shot navigation ability using given abstract $2$-D top-down maps. Like human navigation by reading a paper map, the agent reads the map as an image when navigating in a novel layout, after learning to navigate on a set of training maps. We propose a model-based reinforcement learning approach for this multi-task learning problem, where it jointly learns a hypermodel that takes top-down maps as input and predicts the weights of the transition ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12024","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.12024/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":"2412.12024","created_at":"2026-07-05T09:49:55.586040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12024v1","created_at":"2026-07-05T09:49:55.586040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12024","created_at":"2026-07-05T09:49:55.586040+00:00"},{"alias_kind":"pith_short_12","alias_value":"27FP4AMJTMVF","created_at":"2026-07-05T09:49:55.586040+00:00"},{"alias_kind":"pith_short_16","alias_value":"27FP4AMJTMVFNBK2","created_at":"2026-07-05T09:49:55.586040+00:00"},{"alias_kind":"pith_short_8","alias_value":"27FP4AMJ","created_at":"2026-07-05T09:49:55.586040+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/27FP4AMJTMVFNBK2CAOB7RBUS2","json":"https://pith.science/pith/27FP4AMJTMVFNBK2CAOB7RBUS2.json","graph_json":"https://pith.science/api/pith-number/27FP4AMJTMVFNBK2CAOB7RBUS2/graph.json","events_json":"https://pith.science/api/pith-number/27FP4AMJTMVFNBK2CAOB7RBUS2/events.json","paper":"https://pith.science/paper/27FP4AMJ"},"agent_actions":{"view_html":"https://pith.science/pith/27FP4AMJTMVFNBK2CAOB7RBUS2","download_json":"https://pith.science/pith/27FP4AMJTMVFNBK2CAOB7RBUS2.json","view_paper":"https://pith.science/paper/27FP4AMJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12024&json=true","fetch_graph":"https://pith.science/api/pith-number/27FP4AMJTMVFNBK2CAOB7RBUS2/graph.json","fetch_events":"https://pith.science/api/pith-number/27FP4AMJTMVFNBK2CAOB7RBUS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27FP4AMJTMVFNBK2CAOB7RBUS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27FP4AMJTMVFNBK2CAOB7RBUS2/action/storage_attestation","attest_author":"https://pith.science/pith/27FP4AMJTMVFNBK2CAOB7RBUS2/action/author_attestation","sign_citation":"https://pith.science/pith/27FP4AMJTMVFNBK2CAOB7RBUS2/action/citation_signature","submit_replication":"https://pith.science/pith/27FP4AMJTMVFNBK2CAOB7RBUS2/action/replication_record"}},"created_at":"2026-07-05T09:49:55.586040+00:00","updated_at":"2026-07-05T09:49:55.586040+00:00"}