{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4GK37WU5FSHFD2BWUW3X32BIXD","short_pith_number":"pith:4GK37WU5","schema_version":"1.0","canonical_sha256":"e195bfda9d2c8e51e836a5b77de828b8ddc67d5b5b74429978725d1c0979e3aa","source":{"kind":"arxiv","id":"2403.06966","version":2},"attestation_state":"computed","paper":{"title":"Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Aleksandar Taranovic, Gerhard Neumann, Onur Celik","submitted_at":"2024-03-11T17:49:18Z","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"},"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":"2403.06966","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T17:49:18Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"82a30f154edd6b8e25ed118d0374b27554ea2677a3bb453373126b2043a040fd","abstract_canon_sha256":"f5e21650bc4d4a455ad508e2fd05295c8a0196c253392158e5ecda52094770a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:23.987640Z","signature_b64":"lRHeAb4ARh+hueegzcDjVhlubfnYSJjqfmxZ22mO4jHfgmDUbh0Hx6qZvZwCgA3II+ACp3G3J0TCO//uGueACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e195bfda9d2c8e51e836a5b77de828b8ddc67d5b5b74429978725d1c0979e3aa","last_reissued_at":"2026-07-05T08:29:23.987159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:23.987159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Aleksandar Taranovic, Gerhard Neumann, Onur Celik","submitted_at":"2024-03-11T17:49:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06966","kind":"arxiv","version":2},"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/2403.06966/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":"2403.06966","created_at":"2026-07-05T08:29:23.987210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06966v2","created_at":"2026-07-05T08:29:23.987210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06966","created_at":"2026-07-05T08:29:23.987210+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GK37WU5FSHF","created_at":"2026-07-05T08:29:23.987210+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GK37WU5FSHFD2BW","created_at":"2026-07-05T08:29:23.987210+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GK37WU5","created_at":"2026-07-05T08:29:23.987210+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12953","citing_title":"Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4GK37WU5FSHFD2BWUW3X32BIXD","json":"https://pith.science/pith/4GK37WU5FSHFD2BWUW3X32BIXD.json","graph_json":"https://pith.science/api/pith-number/4GK37WU5FSHFD2BWUW3X32BIXD/graph.json","events_json":"https://pith.science/api/pith-number/4GK37WU5FSHFD2BWUW3X32BIXD/events.json","paper":"https://pith.science/paper/4GK37WU5"},"agent_actions":{"view_html":"https://pith.science/pith/4GK37WU5FSHFD2BWUW3X32BIXD","download_json":"https://pith.science/pith/4GK37WU5FSHFD2BWUW3X32BIXD.json","view_paper":"https://pith.science/paper/4GK37WU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06966&json=true","fetch_graph":"https://pith.science/api/pith-number/4GK37WU5FSHFD2BWUW3X32BIXD/graph.json","fetch_events":"https://pith.science/api/pith-number/4GK37WU5FSHFD2BWUW3X32BIXD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GK37WU5FSHFD2BWUW3X32BIXD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GK37WU5FSHFD2BWUW3X32BIXD/action/storage_attestation","attest_author":"https://pith.science/pith/4GK37WU5FSHFD2BWUW3X32BIXD/action/author_attestation","sign_citation":"https://pith.science/pith/4GK37WU5FSHFD2BWUW3X32BIXD/action/citation_signature","submit_replication":"https://pith.science/pith/4GK37WU5FSHFD2BWUW3X32BIXD/action/replication_record"}},"created_at":"2026-07-05T08:29:23.987210+00:00","updated_at":"2026-07-05T08:29:23.987210+00:00"}