{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JC5KSBFNKVLMARK3GWZ722YD2D","short_pith_number":"pith:JC5KSBFN","schema_version":"1.0","canonical_sha256":"48baa904ad5556c0455b35b3fd6b03d0dfd86a112556a3626973839e76f87a89","source":{"kind":"arxiv","id":"2301.05635","version":1},"attestation_state":"computed","paper":{"title":"Time-Myopic Go-Explore: Learning A State Representation for the Go-Explore Paradigm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jan Robine, Marc H\\\"oftmann, Stefan Harmeling","submitted_at":"2023-01-13T16:13:44Z","abstract_excerpt":"Very large state spaces with a sparse reward signal are difficult to explore. The lack of a sophisticated guidance results in a poor performance for numerous reinforcement learning algorithms. In these cases, the commonly used random exploration is often not helpful. The literature shows that this kind of environments require enormous efforts to systematically explore large chunks of the state space. Learned state representations can help here to improve the search by providing semantic context and build a structure on top of the raw observations. In this work we introduce a novel time-myopic "},"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":"2301.05635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-13T16:13:44Z","cross_cats_sorted":[],"title_canon_sha256":"a859d200e28fd2a5e05b9d9158b0d7f735b021910e172e745a1c19939e14aa87","abstract_canon_sha256":"3bd76bb9d9fa23929aa9ff358685136c71c098c4ee657568723b8a0502f66973"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:55.168904Z","signature_b64":"4xuIddKrxUU+qvnv9cZenJAuicMGwg7vglN2nVZFSsbIQxpq7ZSkDy9hqwz+lsXteUB49eJ9cdkqaw7JC5IdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48baa904ad5556c0455b35b3fd6b03d0dfd86a112556a3626973839e76f87a89","last_reissued_at":"2026-07-05T05:32:55.168528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:55.168528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time-Myopic Go-Explore: Learning A State Representation for the Go-Explore Paradigm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jan Robine, Marc H\\\"oftmann, Stefan Harmeling","submitted_at":"2023-01-13T16:13:44Z","abstract_excerpt":"Very large state spaces with a sparse reward signal are difficult to explore. The lack of a sophisticated guidance results in a poor performance for numerous reinforcement learning algorithms. In these cases, the commonly used random exploration is often not helpful. The literature shows that this kind of environments require enormous efforts to systematically explore large chunks of the state space. Learned state representations can help here to improve the search by providing semantic context and build a structure on top of the raw observations. In this work we introduce a novel time-myopic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05635","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/2301.05635/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":"2301.05635","created_at":"2026-07-05T05:32:55.168584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.05635v1","created_at":"2026-07-05T05:32:55.168584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05635","created_at":"2026-07-05T05:32:55.168584+00:00"},{"alias_kind":"pith_short_12","alias_value":"JC5KSBFNKVLM","created_at":"2026-07-05T05:32:55.168584+00:00"},{"alias_kind":"pith_short_16","alias_value":"JC5KSBFNKVLMARK3","created_at":"2026-07-05T05:32:55.168584+00:00"},{"alias_kind":"pith_short_8","alias_value":"JC5KSBFN","created_at":"2026-07-05T05:32:55.168584+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/JC5KSBFNKVLMARK3GWZ722YD2D","json":"https://pith.science/pith/JC5KSBFNKVLMARK3GWZ722YD2D.json","graph_json":"https://pith.science/api/pith-number/JC5KSBFNKVLMARK3GWZ722YD2D/graph.json","events_json":"https://pith.science/api/pith-number/JC5KSBFNKVLMARK3GWZ722YD2D/events.json","paper":"https://pith.science/paper/JC5KSBFN"},"agent_actions":{"view_html":"https://pith.science/pith/JC5KSBFNKVLMARK3GWZ722YD2D","download_json":"https://pith.science/pith/JC5KSBFNKVLMARK3GWZ722YD2D.json","view_paper":"https://pith.science/paper/JC5KSBFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.05635&json=true","fetch_graph":"https://pith.science/api/pith-number/JC5KSBFNKVLMARK3GWZ722YD2D/graph.json","fetch_events":"https://pith.science/api/pith-number/JC5KSBFNKVLMARK3GWZ722YD2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JC5KSBFNKVLMARK3GWZ722YD2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JC5KSBFNKVLMARK3GWZ722YD2D/action/storage_attestation","attest_author":"https://pith.science/pith/JC5KSBFNKVLMARK3GWZ722YD2D/action/author_attestation","sign_citation":"https://pith.science/pith/JC5KSBFNKVLMARK3GWZ722YD2D/action/citation_signature","submit_replication":"https://pith.science/pith/JC5KSBFNKVLMARK3GWZ722YD2D/action/replication_record"}},"created_at":"2026-07-05T05:32:55.168584+00:00","updated_at":"2026-07-05T05:32:55.168584+00:00"}