{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CDZHI3P5TDWN4KSBDVPIYPF2KB","short_pith_number":"pith:CDZHI3P5","schema_version":"1.0","canonical_sha256":"10f2746dfd98ecde2a411d5e8c3cba5077a42e7f377ea9b05bb5c2cd717a131c","source":{"kind":"arxiv","id":"2407.08464","version":2},"attestation_state":"computed","paper":{"title":"TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Junik Bae, Kwanyoung Park, Youngwoon Lee","submitted_at":"2024-07-11T13:01:18Z","abstract_excerpt":"Unsupervised goal-conditioned reinforcement learning (GCRL) is a promising paradigm for developing diverse robotic skills without external supervision. However, existing unsupervised GCRL methods often struggle to cover a wide range of states in complex environments due to their limited exploration and sparse or noisy rewards for GCRL. To overcome these challenges, we propose a novel unsupervised GCRL method that leverages TemporaL Distance-aware Representations (TLDR). Based on temporal distance, TLDR selects faraway goals to initiate exploration and computes intrinsic exploration rewards and"},"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":"2407.08464","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-11T13:01:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c92b5bf15435bbcc2cb9a3233804fca6462e52fa11ba9a058adba8b2c6f55e9","abstract_canon_sha256":"fdd26f23b9fd2e1f8fbdfe1ff9f0676029f5ba0d1ce0b68f1112f2ebcb271637"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:51.466025Z","signature_b64":"vs5gniVlHl9HbOl1EQGtyjF6dktQRmLG6ni9pRHS8bmJMcmFVczNV6JpDAZrL0TxWQ+6lVUdKEMVq+LSzMGOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10f2746dfd98ecde2a411d5e8c3cba5077a42e7f377ea9b05bb5c2cd717a131c","last_reissued_at":"2026-07-05T09:45:51.465500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:51.465500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Junik Bae, Kwanyoung Park, Youngwoon Lee","submitted_at":"2024-07-11T13:01:18Z","abstract_excerpt":"Unsupervised goal-conditioned reinforcement learning (GCRL) is a promising paradigm for developing diverse robotic skills without external supervision. However, existing unsupervised GCRL methods often struggle to cover a wide range of states in complex environments due to their limited exploration and sparse or noisy rewards for GCRL. To overcome these challenges, we propose a novel unsupervised GCRL method that leverages TemporaL Distance-aware Representations (TLDR). Based on temporal distance, TLDR selects faraway goals to initiate exploration and computes intrinsic exploration rewards and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08464","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.08464/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":"2407.08464","created_at":"2026-07-05T09:45:51.465564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08464v2","created_at":"2026-07-05T09:45:51.465564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08464","created_at":"2026-07-05T09:45:51.465564+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDZHI3P5TDWN","created_at":"2026-07-05T09:45:51.465564+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDZHI3P5TDWN4KSB","created_at":"2026-07-05T09:45:51.465564+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDZHI3P5","created_at":"2026-07-05T09:45:51.465564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22164","citing_title":"Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2510.09096","citing_title":"When a Robot is More Capable than a Human: Learning from Constrained Demonstrators","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07278","citing_title":"Predictive but Not Plannable: RC-aux for Latent World Models","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDZHI3P5TDWN4KSBDVPIYPF2KB","json":"https://pith.science/pith/CDZHI3P5TDWN4KSBDVPIYPF2KB.json","graph_json":"https://pith.science/api/pith-number/CDZHI3P5TDWN4KSBDVPIYPF2KB/graph.json","events_json":"https://pith.science/api/pith-number/CDZHI3P5TDWN4KSBDVPIYPF2KB/events.json","paper":"https://pith.science/paper/CDZHI3P5"},"agent_actions":{"view_html":"https://pith.science/pith/CDZHI3P5TDWN4KSBDVPIYPF2KB","download_json":"https://pith.science/pith/CDZHI3P5TDWN4KSBDVPIYPF2KB.json","view_paper":"https://pith.science/paper/CDZHI3P5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08464&json=true","fetch_graph":"https://pith.science/api/pith-number/CDZHI3P5TDWN4KSBDVPIYPF2KB/graph.json","fetch_events":"https://pith.science/api/pith-number/CDZHI3P5TDWN4KSBDVPIYPF2KB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDZHI3P5TDWN4KSBDVPIYPF2KB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDZHI3P5TDWN4KSBDVPIYPF2KB/action/storage_attestation","attest_author":"https://pith.science/pith/CDZHI3P5TDWN4KSBDVPIYPF2KB/action/author_attestation","sign_citation":"https://pith.science/pith/CDZHI3P5TDWN4KSBDVPIYPF2KB/action/citation_signature","submit_replication":"https://pith.science/pith/CDZHI3P5TDWN4KSBDVPIYPF2KB/action/replication_record"}},"created_at":"2026-07-05T09:45:51.465564+00:00","updated_at":"2026-07-05T09:45:51.465564+00:00"}