{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DDWUDRH4M3OKTLAAGRPP35SN4O","short_pith_number":"pith:DDWUDRH4","schema_version":"1.0","canonical_sha256":"18ed41c4fc66dca9ac00345efdf64de3b842cc4233350e5b7d38f0bcd126fa52","source":{"kind":"arxiv","id":"2002.03647","version":4},"attestation_state":"computed","paper":{"title":"Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Trott, Caiming Xiong, Jordi Torres, Richard Socher, V\\'ictor Campos, Xavier Giro-i-Nieto","submitted_at":"2020-02-10T10:49:53Z","abstract_excerpt":"Acquiring abilities in the absence of a task-oriented reward function is at the frontier of reinforcement learning research. This problem has been studied through the lens of empowerment, which draws a connection between option discovery and information theory. Information-theoretic skill discovery methods have garnered much interest from the community, but little research has been conducted in understanding their limitations. Through theoretical analysis and empirical evidence, we show that existing algorithms suffer from a common limitation -- they discover options that provide a poor covera"},"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":"2002.03647","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T10:49:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f8a444a51ea761306a9e002505570239803f0cd50225e1e097cd05a52198e26f","abstract_canon_sha256":"082c033879da4ceae71255e48efd68ac3fda5f92cc87181bda1d86058ee13b9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:57.055978Z","signature_b64":"aminwWcVezt8DdfcVWqs+PjOI5Ft1X8n/J7v39IHPZGHY23GCgA43IHDMGV6nkRMf/jjrUP64rPEi9MIqfesDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18ed41c4fc66dca9ac00345efdf64de3b842cc4233350e5b7d38f0bcd126fa52","last_reissued_at":"2026-07-05T01:23:57.055469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:57.055469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Trott, Caiming Xiong, Jordi Torres, Richard Socher, V\\'ictor Campos, Xavier Giro-i-Nieto","submitted_at":"2020-02-10T10:49:53Z","abstract_excerpt":"Acquiring abilities in the absence of a task-oriented reward function is at the frontier of reinforcement learning research. This problem has been studied through the lens of empowerment, which draws a connection between option discovery and information theory. Information-theoretic skill discovery methods have garnered much interest from the community, but little research has been conducted in understanding their limitations. Through theoretical analysis and empirical evidence, we show that existing algorithms suffer from a common limitation -- they discover options that provide a poor covera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03647","kind":"arxiv","version":4},"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/2002.03647/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":"2002.03647","created_at":"2026-07-05T01:23:57.055518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.03647v4","created_at":"2026-07-05T01:23:57.055518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03647","created_at":"2026-07-05T01:23:57.055518+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDWUDRH4M3OK","created_at":"2026-07-05T01:23:57.055518+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDWUDRH4M3OKTLAA","created_at":"2026-07-05T01:23:57.055518+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDWUDRH4","created_at":"2026-07-05T01:23:57.055518+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/DDWUDRH4M3OKTLAAGRPP35SN4O","json":"https://pith.science/pith/DDWUDRH4M3OKTLAAGRPP35SN4O.json","graph_json":"https://pith.science/api/pith-number/DDWUDRH4M3OKTLAAGRPP35SN4O/graph.json","events_json":"https://pith.science/api/pith-number/DDWUDRH4M3OKTLAAGRPP35SN4O/events.json","paper":"https://pith.science/paper/DDWUDRH4"},"agent_actions":{"view_html":"https://pith.science/pith/DDWUDRH4M3OKTLAAGRPP35SN4O","download_json":"https://pith.science/pith/DDWUDRH4M3OKTLAAGRPP35SN4O.json","view_paper":"https://pith.science/paper/DDWUDRH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.03647&json=true","fetch_graph":"https://pith.science/api/pith-number/DDWUDRH4M3OKTLAAGRPP35SN4O/graph.json","fetch_events":"https://pith.science/api/pith-number/DDWUDRH4M3OKTLAAGRPP35SN4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDWUDRH4M3OKTLAAGRPP35SN4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDWUDRH4M3OKTLAAGRPP35SN4O/action/storage_attestation","attest_author":"https://pith.science/pith/DDWUDRH4M3OKTLAAGRPP35SN4O/action/author_attestation","sign_citation":"https://pith.science/pith/DDWUDRH4M3OKTLAAGRPP35SN4O/action/citation_signature","submit_replication":"https://pith.science/pith/DDWUDRH4M3OKTLAAGRPP35SN4O/action/replication_record"}},"created_at":"2026-07-05T01:23:57.055518+00:00","updated_at":"2026-07-05T01:23:57.055518+00:00"}