{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OIG2SQA436MVLLC3N3GXMUQ3G6","short_pith_number":"pith:OIG2SQA4","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"},"canonical_sha256":"720da9401cdf9955ac5b6ecd76521b37bea8747250000eaefaee27145eab1b0d","source":{"kind":"arxiv","id":"2206.03597","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.03597","created_at":"2026-07-05T06:32:33Z"},{"alias_kind":"arxiv_version","alias_value":"2206.03597v4","created_at":"2026-07-05T06:32:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03597","created_at":"2026-07-05T06:32:33Z"},{"alias_kind":"pith_short_12","alias_value":"OIG2SQA436MV","created_at":"2026-07-05T06:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"OIG2SQA436MVLLC3","created_at":"2026-07-05T06:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"OIG2SQA4","created_at":"2026-07-05T06:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OIG2SQA436MVLLC3N3GXMUQ3G6","target":"record","payload":{"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"},"canonical_sha256":"720da9401cdf9955ac5b6ecd76521b37bea8747250000eaefaee27145eab1b0d","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"},"source_kind":"arxiv","source_id":"2206.03597","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:32:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gIA02BcVnzML5csKjMjmwGjccLKXPCdkJqCNosBWlpB2frTQZ1dPkdER+jUSVWnbOCSM66U/a4zlvWdVTv85Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:45:42.087977Z"},"content_sha256":"62a6820624e8f2e2536ef3102038e67558baa6a81eda96d0622054b07c6a6fbb","schema_version":"1.0","event_id":"sha256:62a6820624e8f2e2536ef3102038e67558baa6a81eda96d0622054b07c6a6fbb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OIG2SQA436MVLLC3N3GXMUQ3G6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:32:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HBtuCl/7JY5JbRNrhHh8keFTwGLztLHdKs4JhbOz7AkqzU4jmENq/HZQt0hCHY020R9dsovMGEQFI0S2uhvVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:45:42.088264Z"},"content_sha256":"5af00b19606b26cfb017d54e693539298fe8dd9b1e7b028d98f02f964045b38f","schema_version":"1.0","event_id":"sha256:5af00b19606b26cfb017d54e693539298fe8dd9b1e7b028d98f02f964045b38f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6/bundle.json","state_url":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OIG2SQA436MVLLC3N3GXMUQ3G6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-31T17:45:42Z","links":{"resolver":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6","bundle":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6/bundle.json","state":"https://pith.science/pith/OIG2SQA436MVLLC3N3GXMUQ3G6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OIG2SQA436MVLLC3N3GXMUQ3G6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OIG2SQA436MVLLC3N3GXMUQ3G6","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":"a13fd7ac86ab9b1101a25b76d2ae4523a5cd38454d7182a384a5178611682a1a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T21:30:58Z","title_canon_sha256":"084eb488b9cf50c71784532b9cfe292ffe6075f6f18d6c282a88dcea5647b5ff"},"schema_version":"1.0","source":{"id":"2206.03597","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.03597","created_at":"2026-07-05T06:32:33Z"},{"alias_kind":"arxiv_version","alias_value":"2206.03597v4","created_at":"2026-07-05T06:32:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03597","created_at":"2026-07-05T06:32:33Z"},{"alias_kind":"pith_short_12","alias_value":"OIG2SQA436MV","created_at":"2026-07-05T06:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"OIG2SQA436MVLLC3","created_at":"2026-07-05T06:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"OIG2SQA4","created_at":"2026-07-05T06:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:5af00b19606b26cfb017d54e693539298fe8dd9b1e7b028d98f02f964045b38f","target":"graph","created_at":"2026-07-05T06:32:33Z","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/2206.03597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"George Konidaris, Haotian Fu, Michael Littman, Saket Tiwari, Shangqun Yu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T21:30:58Z","title":"Meta-Learning Parameterized Skills"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03597","kind":"arxiv","version":4},"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":"sha256:62a6820624e8f2e2536ef3102038e67558baa6a81eda96d0622054b07c6a6fbb","target":"record","created_at":"2026-07-05T06:32:33Z","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":"a13fd7ac86ab9b1101a25b76d2ae4523a5cd38454d7182a384a5178611682a1a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T21:30:58Z","title_canon_sha256":"084eb488b9cf50c71784532b9cfe292ffe6075f6f18d6c282a88dcea5647b5ff"},"schema_version":"1.0","source":{"id":"2206.03597","kind":"arxiv","version":4}},"canonical_sha256":"720da9401cdf9955ac5b6ecd76521b37bea8747250000eaefaee27145eab1b0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"720da9401cdf9955ac5b6ecd76521b37bea8747250000eaefaee27145eab1b0d","first_computed_at":"2026-07-05T06:32:33.467715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:32:33.467715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jFYSB4AGZvKNaqXJ+mloKLlM9FipbZJBzqfK44UroSvqz+nerUjAVfXyTtuKjnUJe+4jBT1cJnrJdehOV2UJCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:32:33.468209Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.03597","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62a6820624e8f2e2536ef3102038e67558baa6a81eda96d0622054b07c6a6fbb","sha256:5af00b19606b26cfb017d54e693539298fe8dd9b1e7b028d98f02f964045b38f"],"state_sha256":"6b13ee26a2c693a012b53119534ccb5d4f55ef296ffccb2218451f7d54ee9bfb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w4IUAafYMaD6Buk/QNHq+uKepU6aF4PLYGirqLU9u0V1H4hJ8d0f7F61Upi/XejKe8v2dI0I8rtiDckBcd0iDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T17:45:42.092238Z","bundle_sha256":"05bc26ab25ea6f41bd905c009059064249f378884cc59876448939ef00c25e4b"}}