{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TKP3XHO6ZHB65EWS26RP4O7YLQ","short_pith_number":"pith:TKP3XHO6","schema_version":"1.0","canonical_sha256":"9a9fbb9ddec9c3ee92d2d7a2fe3bf85c22861add793cf12e0be5554faebbf1ef","source":{"kind":"arxiv","id":"1905.12621","version":1},"attestation_state":"computed","paper":{"title":"Learning latent state representation for speeding up exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Giulia Vezzani, Lorenzo Natale, Pieter Abbeel","submitted_at":"2019-05-27T09:25:16Z","abstract_excerpt":"Exploration is an extremely challenging problem in reinforcement learning, especially in high dimensional state and action spaces and when only sparse rewards are available. Effective representations can indicate which components of the state are task relevant and thus reduce the dimensionality of the space to explore. In this work, we take a representation learning viewpoint on exploration, utilizing prior experience to learn effective latent representations, which can subsequently indicate which regions to explore. Prior experience on separate but related tasks help learn representations of "},"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":"1905.12621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T09:25:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dc96ac0053a2aa0734b8c545783501e7cdc212a62145f6d6671e0683a4bdb0cc","abstract_canon_sha256":"412e99f1c3370f8146f297d4a2ae4c2f4ba41607cf1e4871235aac73b680c8d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:41.886041Z","signature_b64":"ReBKmIDfCPCWezMnn14amNFzEVgjhadhAhYhrKqDdxc5k/u9VwUq+MDindiypqOME7NqJGSAq9wjCDuycfrzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a9fbb9ddec9c3ee92d2d7a2fe3bf85c22861add793cf12e0be5554faebbf1ef","last_reissued_at":"2026-05-17T23:44:41.885547Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:41.885547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning latent state representation for speeding up exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Giulia Vezzani, Lorenzo Natale, Pieter Abbeel","submitted_at":"2019-05-27T09:25:16Z","abstract_excerpt":"Exploration is an extremely challenging problem in reinforcement learning, especially in high dimensional state and action spaces and when only sparse rewards are available. Effective representations can indicate which components of the state are task relevant and thus reduce the dimensionality of the space to explore. In this work, we take a representation learning viewpoint on exploration, utilizing prior experience to learn effective latent representations, which can subsequently indicate which regions to explore. Prior experience on separate but related tasks help learn representations of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12621","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":"1905.12621","created_at":"2026-05-17T23:44:41.885625+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12621v1","created_at":"2026-05-17T23:44:41.885625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12621","created_at":"2026-05-17T23:44:41.885625+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKP3XHO6ZHB6","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKP3XHO6ZHB65EWS","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKP3XHO6","created_at":"2026-05-18T12:33:30.264802+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/TKP3XHO6ZHB65EWS26RP4O7YLQ","json":"https://pith.science/pith/TKP3XHO6ZHB65EWS26RP4O7YLQ.json","graph_json":"https://pith.science/api/pith-number/TKP3XHO6ZHB65EWS26RP4O7YLQ/graph.json","events_json":"https://pith.science/api/pith-number/TKP3XHO6ZHB65EWS26RP4O7YLQ/events.json","paper":"https://pith.science/paper/TKP3XHO6"},"agent_actions":{"view_html":"https://pith.science/pith/TKP3XHO6ZHB65EWS26RP4O7YLQ","download_json":"https://pith.science/pith/TKP3XHO6ZHB65EWS26RP4O7YLQ.json","view_paper":"https://pith.science/paper/TKP3XHO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12621&json=true","fetch_graph":"https://pith.science/api/pith-number/TKP3XHO6ZHB65EWS26RP4O7YLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TKP3XHO6ZHB65EWS26RP4O7YLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKP3XHO6ZHB65EWS26RP4O7YLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKP3XHO6ZHB65EWS26RP4O7YLQ/action/storage_attestation","attest_author":"https://pith.science/pith/TKP3XHO6ZHB65EWS26RP4O7YLQ/action/author_attestation","sign_citation":"https://pith.science/pith/TKP3XHO6ZHB65EWS26RP4O7YLQ/action/citation_signature","submit_replication":"https://pith.science/pith/TKP3XHO6ZHB65EWS26RP4O7YLQ/action/replication_record"}},"created_at":"2026-05-17T23:44:41.885625+00:00","updated_at":"2026-05-17T23:44:41.885625+00:00"}