{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:INQ6BMPKYPQMMLIEKRKGT55BPJ","short_pith_number":"pith:INQ6BMPK","schema_version":"1.0","canonical_sha256":"4361e0b1eac3e0c62d04545469f7a17a7bb50c8c6a74987a19d5748800598d3d","source":{"kind":"arxiv","id":"2302.14242","version":1},"attestation_state":"computed","paper":{"title":"Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Mariano Phielipp, Ruihan Zhao, Sandeep Chinchali, Ufuk Topcu","submitted_at":"2023-02-28T01:54:56Z","abstract_excerpt":"Recent progress in deep reinforcement learning (RL) and computer vision enables artificial agents to solve complex tasks, including locomotion, manipulation and video games from high-dimensional pixel observations. However, domain specific reward functions are often engineered to provide sufficient learning signals, requiring expert knowledge. While it is possible to train vision-based RL agents using only sparse rewards, additional challenges in exploration arise. We present a novel and efficient method to solve sparse-reward robot manipulation tasks from only image observations by utilizing "},"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":"2302.14242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-02-28T01:54:56Z","cross_cats_sorted":[],"title_canon_sha256":"70b52bc7d84331f980477f07f4edbf07e42957a577f02c85d7016bf959e619b4","abstract_canon_sha256":"2b0df03196e7867829cfe7a5b1edfdd7408d5dc8cf3d11f05c37acd8730ae01d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:42.382816Z","signature_b64":"5k/P5hwdvpLq9XSLUzbUhF/S3cTTWcikFK6ZnpEBXmrWWVHZ3T6rGmgyPW0AUl61emdp72dy8b784Jl8xpJUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4361e0b1eac3e0c62d04545469f7a17a7bb50c8c6a74987a19d5748800598d3d","last_reissued_at":"2026-07-05T05:46:42.382394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:42.382394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Mariano Phielipp, Ruihan Zhao, Sandeep Chinchali, Ufuk Topcu","submitted_at":"2023-02-28T01:54:56Z","abstract_excerpt":"Recent progress in deep reinforcement learning (RL) and computer vision enables artificial agents to solve complex tasks, including locomotion, manipulation and video games from high-dimensional pixel observations. However, domain specific reward functions are often engineered to provide sufficient learning signals, requiring expert knowledge. While it is possible to train vision-based RL agents using only sparse rewards, additional challenges in exploration arise. We present a novel and efficient method to solve sparse-reward robot manipulation tasks from only image observations by utilizing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14242","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/2302.14242/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":"2302.14242","created_at":"2026-07-05T05:46:42.382452+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.14242v1","created_at":"2026-07-05T05:46:42.382452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14242","created_at":"2026-07-05T05:46:42.382452+00:00"},{"alias_kind":"pith_short_12","alias_value":"INQ6BMPKYPQM","created_at":"2026-07-05T05:46:42.382452+00:00"},{"alias_kind":"pith_short_16","alias_value":"INQ6BMPKYPQMMLIE","created_at":"2026-07-05T05:46:42.382452+00:00"},{"alias_kind":"pith_short_8","alias_value":"INQ6BMPK","created_at":"2026-07-05T05:46:42.382452+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/INQ6BMPKYPQMMLIEKRKGT55BPJ","json":"https://pith.science/pith/INQ6BMPKYPQMMLIEKRKGT55BPJ.json","graph_json":"https://pith.science/api/pith-number/INQ6BMPKYPQMMLIEKRKGT55BPJ/graph.json","events_json":"https://pith.science/api/pith-number/INQ6BMPKYPQMMLIEKRKGT55BPJ/events.json","paper":"https://pith.science/paper/INQ6BMPK"},"agent_actions":{"view_html":"https://pith.science/pith/INQ6BMPKYPQMMLIEKRKGT55BPJ","download_json":"https://pith.science/pith/INQ6BMPKYPQMMLIEKRKGT55BPJ.json","view_paper":"https://pith.science/paper/INQ6BMPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.14242&json=true","fetch_graph":"https://pith.science/api/pith-number/INQ6BMPKYPQMMLIEKRKGT55BPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/INQ6BMPKYPQMMLIEKRKGT55BPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INQ6BMPKYPQMMLIEKRKGT55BPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INQ6BMPKYPQMMLIEKRKGT55BPJ/action/storage_attestation","attest_author":"https://pith.science/pith/INQ6BMPKYPQMMLIEKRKGT55BPJ/action/author_attestation","sign_citation":"https://pith.science/pith/INQ6BMPKYPQMMLIEKRKGT55BPJ/action/citation_signature","submit_replication":"https://pith.science/pith/INQ6BMPKYPQMMLIEKRKGT55BPJ/action/replication_record"}},"created_at":"2026-07-05T05:46:42.382452+00:00","updated_at":"2026-07-05T05:46:42.382452+00:00"}