{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7AM3ZWZ3SJYU4GYLB7AKFVL4A2","short_pith_number":"pith:7AM3ZWZ3","schema_version":"1.0","canonical_sha256":"f819bcdb3b92714e1b0b0fc0a2d57c06b380e94c1c20f60937f9ee05b07b0cee","source":{"kind":"arxiv","id":"2305.14377","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Discovery of Continuous Skills on a Sphere","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Takahisa Imagawa, Takuya Hiraoka, Yoshimasa Tsuruoka","submitted_at":"2023-05-21T06:29:41Z","abstract_excerpt":"Recently, methods for learning diverse skills to generate various behaviors without external rewards have been actively studied as a form of unsupervised reinforcement learning. However, most of the existing methods learn a finite number of discrete skills, and thus the variety of behaviors that can be exhibited with the learned skills is limited. In this paper, we propose a novel method for learning potentially an infinite number of different skills, which is named discovery of continuous skills on a sphere (DISCS). In DISCS, skills are learned by maximizing mutual information between skills "},"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":"2305.14377","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-21T06:29:41Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"cb83d324d90e46d6293c5fac542837c9ae6d25f7af9d185d7b5e0b91ef896b41","abstract_canon_sha256":"398aaebc65c2e79a355ca89342db51966454b02df214f150543c183e6f66b171"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:56.897967Z","signature_b64":"bldrKxgOu5S/ZLDEu/6lQvlldrG0cVxJv21QS9WR83PPlUD9xUUHuoQrgBRdAOTGv1d2xulXY088JIlyz8+mDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f819bcdb3b92714e1b0b0fc0a2d57c06b380e94c1c20f60937f9ee05b07b0cee","last_reissued_at":"2026-07-05T06:13:56.897559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:56.897559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Discovery of Continuous Skills on a Sphere","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Takahisa Imagawa, Takuya Hiraoka, Yoshimasa Tsuruoka","submitted_at":"2023-05-21T06:29:41Z","abstract_excerpt":"Recently, methods for learning diverse skills to generate various behaviors without external rewards have been actively studied as a form of unsupervised reinforcement learning. However, most of the existing methods learn a finite number of discrete skills, and thus the variety of behaviors that can be exhibited with the learned skills is limited. In this paper, we propose a novel method for learning potentially an infinite number of different skills, which is named discovery of continuous skills on a sphere (DISCS). In DISCS, skills are learned by maximizing mutual information between skills "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14377","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/2305.14377/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":"2305.14377","created_at":"2026-07-05T06:13:56.897615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14377v2","created_at":"2026-07-05T06:13:56.897615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14377","created_at":"2026-07-05T06:13:56.897615+00:00"},{"alias_kind":"pith_short_12","alias_value":"7AM3ZWZ3SJYU","created_at":"2026-07-05T06:13:56.897615+00:00"},{"alias_kind":"pith_short_16","alias_value":"7AM3ZWZ3SJYU4GYL","created_at":"2026-07-05T06:13:56.897615+00:00"},{"alias_kind":"pith_short_8","alias_value":"7AM3ZWZ3","created_at":"2026-07-05T06:13:56.897615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19953","citing_title":"Divide, Discover, Deploy: Factorized Skill Learning with Symmetry and Style Priors","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7AM3ZWZ3SJYU4GYLB7AKFVL4A2","json":"https://pith.science/pith/7AM3ZWZ3SJYU4GYLB7AKFVL4A2.json","graph_json":"https://pith.science/api/pith-number/7AM3ZWZ3SJYU4GYLB7AKFVL4A2/graph.json","events_json":"https://pith.science/api/pith-number/7AM3ZWZ3SJYU4GYLB7AKFVL4A2/events.json","paper":"https://pith.science/paper/7AM3ZWZ3"},"agent_actions":{"view_html":"https://pith.science/pith/7AM3ZWZ3SJYU4GYLB7AKFVL4A2","download_json":"https://pith.science/pith/7AM3ZWZ3SJYU4GYLB7AKFVL4A2.json","view_paper":"https://pith.science/paper/7AM3ZWZ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14377&json=true","fetch_graph":"https://pith.science/api/pith-number/7AM3ZWZ3SJYU4GYLB7AKFVL4A2/graph.json","fetch_events":"https://pith.science/api/pith-number/7AM3ZWZ3SJYU4GYLB7AKFVL4A2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7AM3ZWZ3SJYU4GYLB7AKFVL4A2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7AM3ZWZ3SJYU4GYLB7AKFVL4A2/action/storage_attestation","attest_author":"https://pith.science/pith/7AM3ZWZ3SJYU4GYLB7AKFVL4A2/action/author_attestation","sign_citation":"https://pith.science/pith/7AM3ZWZ3SJYU4GYLB7AKFVL4A2/action/citation_signature","submit_replication":"https://pith.science/pith/7AM3ZWZ3SJYU4GYLB7AKFVL4A2/action/replication_record"}},"created_at":"2026-07-05T06:13:56.897615+00:00","updated_at":"2026-07-05T06:13:56.897615+00:00"}