{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:N3HBPAON35IV6Y5R6VW2OL7X5E","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":"2ff7be6f332a4576ab133d155f666c50109e1c33a19630143b497513f462c973","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-15T08:41:51Z","title_canon_sha256":"26d45f4907762556b4a9af315599bc238d5581cddefebfdeeee729db94241daf"},"schema_version":"1.0","source":{"id":"2110.07940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07940","created_at":"2026-07-05T03:22:51Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07940v1","created_at":"2026-07-05T03:22:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07940","created_at":"2026-07-05T03:22:51Z"},{"alias_kind":"pith_short_12","alias_value":"N3HBPAON35IV","created_at":"2026-07-05T03:22:51Z"},{"alias_kind":"pith_short_16","alias_value":"N3HBPAON35IV6Y5R","created_at":"2026-07-05T03:22:51Z"},{"alias_kind":"pith_short_8","alias_value":"N3HBPAON","created_at":"2026-07-05T03:22:51Z"}],"graph_snapshots":[{"event_id":"sha256:a27be2b64702ea344476afee9d4ff17fc010b67b93c79bc05b21778a978dee8c","target":"graph","created_at":"2026-07-05T03:22:51Z","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/2110.07940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised reinforcement learning aims to train agents to learn a handful of policies or skills in environments without external reward. These pre-trained policies can accelerate learning when endowed with external reward, and can also be used as primitive options in hierarchical reinforcement learning. Conventional approaches of unsupervised skill discovery feed a latent variable to the agent and shed its empowerment on agent's behavior by mutual information (MI) maximization. However, the policies learned by MI-based methods cannot sufficiently explore the state space, despite they can be ","authors_text":"Hongchang Zhang, Jianzhun Shao, Shuncheng He, Xiangyang Ji, Yuhang Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-15T08:41:51Z","title":"Wasserstein Unsupervised Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07940","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":"sha256:789b40dd148d298e6a821478648dc8c510c1aa0164876d5fa2b6407552047a01","target":"record","created_at":"2026-07-05T03:22:51Z","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":"2ff7be6f332a4576ab133d155f666c50109e1c33a19630143b497513f462c973","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-15T08:41:51Z","title_canon_sha256":"26d45f4907762556b4a9af315599bc238d5581cddefebfdeeee729db94241daf"},"schema_version":"1.0","source":{"id":"2110.07940","kind":"arxiv","version":1}},"canonical_sha256":"6ece1781cddf515f63b1f56da72ff7e9252f0f28b8e9ae5306b473db24fed209","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ece1781cddf515f63b1f56da72ff7e9252f0f28b8e9ae5306b473db24fed209","first_computed_at":"2026-07-05T03:22:51.547999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:51.547999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DF9DwNrQ/N1gDY7pq3fEnfaKUm3u5h3LlcErWWp3oSk6/SktB3+5OIWn4HITCB2mER1U7DX9EP2812tDLZOkDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:51.548420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.07940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:789b40dd148d298e6a821478648dc8c510c1aa0164876d5fa2b6407552047a01","sha256:a27be2b64702ea344476afee9d4ff17fc010b67b93c79bc05b21778a978dee8c"],"state_sha256":"0b691e91f705109dcba56f036990d504b921b2130a132b3b5053854a8b7f467e"}