{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4GK37WU5FSHFD2BWUW3X32BIXD","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":"f5e21650bc4d4a455ad508e2fd05295c8a0196c253392158e5ecda52094770a8","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T17:49:18Z","title_canon_sha256":"82a30f154edd6b8e25ed118d0374b27554ea2677a3bb453373126b2043a040fd"},"schema_version":"1.0","source":{"id":"2403.06966","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06966","created_at":"2026-07-05T08:29:23Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06966v2","created_at":"2026-07-05T08:29:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06966","created_at":"2026-07-05T08:29:23Z"},{"alias_kind":"pith_short_12","alias_value":"4GK37WU5FSHF","created_at":"2026-07-05T08:29:23Z"},{"alias_kind":"pith_short_16","alias_value":"4GK37WU5FSHFD2BW","created_at":"2026-07-05T08:29:23Z"},{"alias_kind":"pith_short_8","alias_value":"4GK37WU5","created_at":"2026-07-05T08:29:23Z"}],"graph_snapshots":[{"event_id":"sha256:c9e5b4d5bd31c3238a3cc0677ed178cf3f1ff7edbfa1996e466351d9a4c57e3c","target":"graph","created_at":"2026-07-05T08:29:23Z","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/2403.06966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is a powerful approach for acquiring a good-performing policy. However, learning diverse skills is challenging in RL due to the commonly used Gaussian policy parameterization. We propose \\textbf{Di}verse \\textbf{Skil}l \\textbf{L}earning (Di-SkilL\\footnote{Videos and code are available on the project webpage: \\url{https://alrhub.github.io/di-skill-website/}}), an RL method for learning diverse skills using Mixture of Experts, where each expert formalizes a skill as a contextual motion primitive. Di-SkilL optimizes each expert and its associate context distribution to","authors_text":"Aleksandar Taranovic, Gerhard Neumann, Onur Celik","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T17:49:18Z","title":"Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06966","kind":"arxiv","version":2},"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":"sha256:7fdd79405565e8812c5778239a68e93430bc33718843038e546639a572e69025","target":"record","created_at":"2026-07-05T08:29:23Z","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":"f5e21650bc4d4a455ad508e2fd05295c8a0196c253392158e5ecda52094770a8","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T17:49:18Z","title_canon_sha256":"82a30f154edd6b8e25ed118d0374b27554ea2677a3bb453373126b2043a040fd"},"schema_version":"1.0","source":{"id":"2403.06966","kind":"arxiv","version":2}},"canonical_sha256":"e195bfda9d2c8e51e836a5b77de828b8ddc67d5b5b74429978725d1c0979e3aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e195bfda9d2c8e51e836a5b77de828b8ddc67d5b5b74429978725d1c0979e3aa","first_computed_at":"2026-07-05T08:29:23.987159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:23.987159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lRHeAb4ARh+hueegzcDjVhlubfnYSJjqfmxZ22mO4jHfgmDUbh0Hx6qZvZwCgA3II+ACp3G3J0TCO//uGueACA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:23.987640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06966","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fdd79405565e8812c5778239a68e93430bc33718843038e546639a572e69025","sha256:c9e5b4d5bd31c3238a3cc0677ed178cf3f1ff7edbfa1996e466351d9a4c57e3c"],"state_sha256":"d84868a43e98974a29d9ca8ff1152dab14afb0f5039da697deb916dabdebf56d"}