{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UCTT63YZKAFJRU2BR3RNEZJSEW","short_pith_number":"pith:UCTT63YZ","schema_version":"1.0","canonical_sha256":"a0a73f6f19500a98d3418ee2d265322589297c8429f05310946ed13f3167b391","source":{"kind":"arxiv","id":"2405.16030","version":1},"attestation_state":"computed","paper":{"title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Kang Xu, Qiaosheng Zhang, Rushuai Yang, Ting Xiao, Xuelong Li, Yi Chen","submitted_at":"2024-05-25T03:07:56Z","abstract_excerpt":"Unsupervised Reinforcement Learning (RL) provides a promising paradigm for learning useful behaviors via reward-free per-training. Existing methods for unsupervised RL mainly conduct empowerment-driven skill discovery or entropy-based exploration. However, empowerment often leads to static skills, and pure exploration only maximizes the state coverage rather than learning useful behaviors. In this paper, we propose a novel unsupervised RL framework via an ensemble of skills, where each skill performs partition exploration based on the state prototypes. Thus, each skill can explore the clustere"},"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":"2405.16030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T03:07:56Z","cross_cats_sorted":[],"title_canon_sha256":"63f160c536b877507859077266e5b5742c9d769dc7f1a57988fde859d2fcdf3e","abstract_canon_sha256":"bef709a7893e3ae976c854c3d384e4887f627058694e79741ce862d6d12dd4bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:00.896858Z","signature_b64":"H2Xy2FDYX9S+iwyMjmViAT0c1emEqHmfqa5fFuzqE5VbkLLnEFzV5t0rIi9FnJdkkHeerYYYYtw/MKBIqU8CDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0a73f6f19500a98d3418ee2d265322589297c8429f05310946ed13f3167b391","last_reissued_at":"2026-07-05T08:23:00.896418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:00.896418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Kang Xu, Qiaosheng Zhang, Rushuai Yang, Ting Xiao, Xuelong Li, Yi Chen","submitted_at":"2024-05-25T03:07:56Z","abstract_excerpt":"Unsupervised Reinforcement Learning (RL) provides a promising paradigm for learning useful behaviors via reward-free per-training. Existing methods for unsupervised RL mainly conduct empowerment-driven skill discovery or entropy-based exploration. However, empowerment often leads to static skills, and pure exploration only maximizes the state coverage rather than learning useful behaviors. In this paper, we propose a novel unsupervised RL framework via an ensemble of skills, where each skill performs partition exploration based on the state prototypes. Thus, each skill can explore the clustere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16030","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/2405.16030/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":"2405.16030","created_at":"2026-07-05T08:23:00.896478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16030v1","created_at":"2026-07-05T08:23:00.896478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16030","created_at":"2026-07-05T08:23:00.896478+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCTT63YZKAFJ","created_at":"2026-07-05T08:23:00.896478+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCTT63YZKAFJRU2B","created_at":"2026-07-05T08:23:00.896478+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCTT63YZ","created_at":"2026-07-05T08:23:00.896478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07279","citing_title":"Exploratory Diffusion Model for Unsupervised Reinforcement Learning","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UCTT63YZKAFJRU2BR3RNEZJSEW","json":"https://pith.science/pith/UCTT63YZKAFJRU2BR3RNEZJSEW.json","graph_json":"https://pith.science/api/pith-number/UCTT63YZKAFJRU2BR3RNEZJSEW/graph.json","events_json":"https://pith.science/api/pith-number/UCTT63YZKAFJRU2BR3RNEZJSEW/events.json","paper":"https://pith.science/paper/UCTT63YZ"},"agent_actions":{"view_html":"https://pith.science/pith/UCTT63YZKAFJRU2BR3RNEZJSEW","download_json":"https://pith.science/pith/UCTT63YZKAFJRU2BR3RNEZJSEW.json","view_paper":"https://pith.science/paper/UCTT63YZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16030&json=true","fetch_graph":"https://pith.science/api/pith-number/UCTT63YZKAFJRU2BR3RNEZJSEW/graph.json","fetch_events":"https://pith.science/api/pith-number/UCTT63YZKAFJRU2BR3RNEZJSEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCTT63YZKAFJRU2BR3RNEZJSEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCTT63YZKAFJRU2BR3RNEZJSEW/action/storage_attestation","attest_author":"https://pith.science/pith/UCTT63YZKAFJRU2BR3RNEZJSEW/action/author_attestation","sign_citation":"https://pith.science/pith/UCTT63YZKAFJRU2BR3RNEZJSEW/action/citation_signature","submit_replication":"https://pith.science/pith/UCTT63YZKAFJRU2BR3RNEZJSEW/action/replication_record"}},"created_at":"2026-07-05T08:23:00.896478+00:00","updated_at":"2026-07-05T08:23:00.896478+00:00"}