{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OIG2SQA436MVLLC3N3GXMUQ3G6","short_pith_number":"pith:OIG2SQA4","schema_version":"1.0","canonical_sha256":"720da9401cdf9955ac5b6ecd76521b37bea8747250000eaefaee27145eab1b0d","source":{"kind":"arxiv","id":"2206.03597","version":4},"attestation_state":"computed","paper":{"title":"Meta-Learning Parameterized Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"George Konidaris, Haotian Fu, Michael Littman, Saket Tiwari, Shangqun Yu","submitted_at":"2022-06-07T21:30:58Z","abstract_excerpt":"We propose a novel parameterized skill-learning algorithm that aims to learn transferable parameterized skills and synthesize them into a new action space that supports efficient learning in long-horizon tasks. We propose to leverage off-policy Meta-RL combined with a trajectory-centric smoothness term to learn a set of parameterized skills. Our agent can use these learned skills to construct a three-level hierarchical framework that models a Temporally-extended Parameterized Action Markov Decision Process. We empirically demonstrate that the proposed algorithms enable an agent to solve a set "},"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":"2206.03597","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T21:30:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"084eb488b9cf50c71784532b9cfe292ffe6075f6f18d6c282a88dcea5647b5ff","abstract_canon_sha256":"a13fd7ac86ab9b1101a25b76d2ae4523a5cd38454d7182a384a5178611682a1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:33.468209Z","signature_b64":"jFYSB4AGZvKNaqXJ+mloKLlM9FipbZJBzqfK44UroSvqz+nerUjAVfXyTtuKjnUJe+4jBT1cJnrJdehOV2UJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"720da9401cdf9955ac5b6ecd76521b37bea8747250000eaefaee27145eab1b0d","last_reissued_at":"2026-07-05T06:32:33.467715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:33.467715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning Parameterized Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"George Konidaris, Haotian Fu, Michael Littman, Saket Tiwari, Shangqun Yu","submitted_at":"2022-06-07T21:30:58Z","abstract_excerpt":"We propose a novel parameterized skill-learning algorithm that aims to learn transferable parameterized skills and synthesize them into a new action space that supports efficient learning in long-horizon tasks. We propose to leverage off-policy Meta-RL combined with a trajectory-centric smoothness term to learn a set of parameterized skills. Our agent can use these learned skills to construct a three-level hierarchical framework that models a Temporally-extended Parameterized Action Markov Decision Process. We empirically demonstrate that the proposed algorithms enable an agent to solve a set "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03597","kind":"arxiv","version":4},"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/2206.03597/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":"2206.03597","created_at":"2026-07-05T06:32:33.467780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.03597v4","created_at":"2026-07-05T06:32:33.467780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03597","created_at":"2026-07-05T06:32:33.467780+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIG2SQA436MV","created_at":"2026-07-05T06:32:33.467780+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIG2SQA436MVLLC3","created_at":"2026-07-05T06:32:33.467780+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIG2SQA4","created_at":"2026-07-05T06:32:33.467780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02834","citing_title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6","json":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6.json","graph_json":"https://pith.science/api/pith-number/OIG2SQA436MVLLC3N3GXMUQ3G6/graph.json","events_json":"https://pith.science/api/pith-number/OIG2SQA436MVLLC3N3GXMUQ3G6/events.json","paper":"https://pith.science/paper/OIG2SQA4"},"agent_actions":{"view_html":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6","download_json":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6.json","view_paper":"https://pith.science/paper/OIG2SQA4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.03597&json=true","fetch_graph":"https://pith.science/api/pith-number/OIG2SQA436MVLLC3N3GXMUQ3G6/graph.json","fetch_events":"https://pith.science/api/pith-number/OIG2SQA436MVLLC3N3GXMUQ3G6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6/action/storage_attestation","attest_author":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6/action/author_attestation","sign_citation":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6/action/citation_signature","submit_replication":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6/action/replication_record"}},"created_at":"2026-07-05T06:32:33.467780+00:00","updated_at":"2026-07-05T06:32:33.467780+00:00"}