{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UCTT63YZKAFJRU2BR3RNEZJSEW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bef709a7893e3ae976c854c3d384e4887f627058694e79741ce862d6d12dd4bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T03:07:56Z","title_canon_sha256":"63f160c536b877507859077266e5b5742c9d769dc7f1a57988fde859d2fcdf3e"},"schema_version":"1.0","source":{"id":"2405.16030","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16030","created_at":"2026-07-05T08:23:00Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16030v1","created_at":"2026-07-05T08:23:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16030","created_at":"2026-07-05T08:23:00Z"},{"alias_kind":"pith_short_12","alias_value":"UCTT63YZKAFJ","created_at":"2026-07-05T08:23:00Z"},{"alias_kind":"pith_short_16","alias_value":"UCTT63YZKAFJRU2B","created_at":"2026-07-05T08:23:00Z"},{"alias_kind":"pith_short_8","alias_value":"UCTT63YZ","created_at":"2026-07-05T08:23:00Z"}],"graph_snapshots":[{"event_id":"sha256:218df86754edf032467274baa69d6de8a4c2d2075d5b678f064509799aa5b663","target":"graph","created_at":"2026-07-05T08:23:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.16030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenjia Bai, Kang Xu, Qiaosheng Zhang, Rushuai Yang, Ting Xiao, Xuelong Li, Yi Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T03:07:56Z","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16030","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ab51b8b4742ec81eb890d9a46c6ae30d13316a8bf75f4945986ac5adba17af73","target":"record","created_at":"2026-07-05T08:23:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bef709a7893e3ae976c854c3d384e4887f627058694e79741ce862d6d12dd4bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T03:07:56Z","title_canon_sha256":"63f160c536b877507859077266e5b5742c9d769dc7f1a57988fde859d2fcdf3e"},"schema_version":"1.0","source":{"id":"2405.16030","kind":"arxiv","version":1}},"canonical_sha256":"a0a73f6f19500a98d3418ee2d265322589297c8429f05310946ed13f3167b391","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0a73f6f19500a98d3418ee2d265322589297c8429f05310946ed13f3167b391","first_computed_at":"2026-07-05T08:23:00.896418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:00.896418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H2Xy2FDYX9S+iwyMjmViAT0c1emEqHmfqa5fFuzqE5VbkLLnEFzV5t0rIi9FnJdkkHeerYYYYtw/MKBIqU8CDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:00.896858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16030","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab51b8b4742ec81eb890d9a46c6ae30d13316a8bf75f4945986ac5adba17af73","sha256:218df86754edf032467274baa69d6de8a4c2d2075d5b678f064509799aa5b663"],"state_sha256":"63d6caa0b6fc121ee0d0b106a7b5bfdd26244237d3fa643cbdfb002f211c23be"}