{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AHO6XK3E3GCRNT4FDWWEZMBABX","short_pith_number":"pith:AHO6XK3E","schema_version":"1.0","canonical_sha256":"01ddebab64d98516cf851dac4cb0200dfadac28aa739486a1a7752a5f2523a1a","source":{"kind":"arxiv","id":"2506.14420","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Skill Discovery through Skill Regions Differentiation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Jiakun Zheng, Kang Xu, Peng Liu, Qiaosheng Zhang, Rushuai Yang, Ting Xiao","submitted_at":"2025-06-17T11:30:04Z","abstract_excerpt":"Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However, entropy-based exploration struggles in large-scale state spaces (e.g., images), and empowerment-based methods with Mutual Information (MI) estimations have limitations in state exploration. To address these challenges, we propose a novel skill discovery objective that maximizes the deviation of the state density of one skill from the explored regions of other"},"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":"2506.14420","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T11:30:04Z","cross_cats_sorted":[],"title_canon_sha256":"bce8ad4637e4b6414221c5255e5ca9d7289a196fba69bac84ea68b4b4481dcfa","abstract_canon_sha256":"103dc1d10b296c52c91411a5ce42147e9286ec3f002baf277bb19937d2c998e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:56.198145Z","signature_b64":"GBhfUlZp2jTkzCVYkHCQw7RdmkMqEx01J2YehluXhD2lfjgDFzUIjLxcbYST+EqyXSrlhDe4gXHp7VqWpoGpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01ddebab64d98516cf851dac4cb0200dfadac28aa739486a1a7752a5f2523a1a","last_reissued_at":"2026-07-05T11:22:56.197681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:56.197681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Skill Discovery through Skill Regions Differentiation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Jiakun Zheng, Kang Xu, Peng Liu, Qiaosheng Zhang, Rushuai Yang, Ting Xiao","submitted_at":"2025-06-17T11:30:04Z","abstract_excerpt":"Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However, entropy-based exploration struggles in large-scale state spaces (e.g., images), and empowerment-based methods with Mutual Information (MI) estimations have limitations in state exploration. To address these challenges, we propose a novel skill discovery objective that maximizes the deviation of the state density of one skill from the explored regions of other"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14420","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/2506.14420/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":"2506.14420","created_at":"2026-07-05T11:22:56.197745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14420v1","created_at":"2026-07-05T11:22:56.197745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14420","created_at":"2026-07-05T11:22:56.197745+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHO6XK3E3GCR","created_at":"2026-07-05T11:22:56.197745+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHO6XK3E3GCRNT4F","created_at":"2026-07-05T11:22:56.197745+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHO6XK3E","created_at":"2026-07-05T11:22:56.197745+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/AHO6XK3E3GCRNT4FDWWEZMBABX","json":"https://pith.science/pith/AHO6XK3E3GCRNT4FDWWEZMBABX.json","graph_json":"https://pith.science/api/pith-number/AHO6XK3E3GCRNT4FDWWEZMBABX/graph.json","events_json":"https://pith.science/api/pith-number/AHO6XK3E3GCRNT4FDWWEZMBABX/events.json","paper":"https://pith.science/paper/AHO6XK3E"},"agent_actions":{"view_html":"https://pith.science/pith/AHO6XK3E3GCRNT4FDWWEZMBABX","download_json":"https://pith.science/pith/AHO6XK3E3GCRNT4FDWWEZMBABX.json","view_paper":"https://pith.science/paper/AHO6XK3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14420&json=true","fetch_graph":"https://pith.science/api/pith-number/AHO6XK3E3GCRNT4FDWWEZMBABX/graph.json","fetch_events":"https://pith.science/api/pith-number/AHO6XK3E3GCRNT4FDWWEZMBABX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHO6XK3E3GCRNT4FDWWEZMBABX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHO6XK3E3GCRNT4FDWWEZMBABX/action/storage_attestation","attest_author":"https://pith.science/pith/AHO6XK3E3GCRNT4FDWWEZMBABX/action/author_attestation","sign_citation":"https://pith.science/pith/AHO6XK3E3GCRNT4FDWWEZMBABX/action/citation_signature","submit_replication":"https://pith.science/pith/AHO6XK3E3GCRNT4FDWWEZMBABX/action/replication_record"}},"created_at":"2026-07-05T11:22:56.197745+00:00","updated_at":"2026-07-05T11:22:56.197745+00:00"}