{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QMZO4XRSZ7SLHLBXKP4JBPPKPX","short_pith_number":"pith:QMZO4XRS","schema_version":"1.0","canonical_sha256":"8332ee5e32cfe4b3ac3753f890bdea7df6e8a99a803306ec4b24490dafd15b92","source":{"kind":"arxiv","id":"1710.09767","version":1},"attestation_state":"computed","paper":{"title":"Meta Learning Shared Hierarchies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"John Schulman, Jonathan Ho, Kevin Frans, Pieter Abbeel, Xi Chen","submitted_at":"2017-10-26T15:43:33Z","abstract_excerpt":"We develop a metalearning approach for learning hierarchically structured policies, improving sample efficiency on unseen tasks through the use of shared primitives---policies that are executed for large numbers of timesteps. Specifically, a set of primitives are shared within a distribution of tasks, and are switched between by task-specific policies. We provide a concrete metric for measuring the strength of such hierarchies, leading to an optimization problem for quickly reaching high reward on unseen tasks. We then present an algorithm to solve this problem end-to-end through the use of an"},"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":"1710.09767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-26T15:43:33Z","cross_cats_sorted":[],"title_canon_sha256":"c09996fd77f0f69353c40639788ffc323a32999911ea6b3149f4f5d34382e1be","abstract_canon_sha256":"56bdf2cf57f49c95bfc717c40b5c85dafe9277481f56521ee0ffe8c86601522e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:56.520259Z","signature_b64":"6t3CxxruJy6jAEKEVNrPM/TK8YNdd56LAi8CY1w9WDqvmRA2g0qd8OcMOD0JjmoM5V8kbGcOhFj1BSCFlodnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8332ee5e32cfe4b3ac3753f890bdea7df6e8a99a803306ec4b24490dafd15b92","last_reissued_at":"2026-05-18T00:31:56.519704Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:56.519704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta Learning Shared Hierarchies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"John Schulman, Jonathan Ho, Kevin Frans, Pieter Abbeel, Xi Chen","submitted_at":"2017-10-26T15:43:33Z","abstract_excerpt":"We develop a metalearning approach for learning hierarchically structured policies, improving sample efficiency on unseen tasks through the use of shared primitives---policies that are executed for large numbers of timesteps. Specifically, a set of primitives are shared within a distribution of tasks, and are switched between by task-specific policies. We provide a concrete metric for measuring the strength of such hierarchies, leading to an optimization problem for quickly reaching high reward on unseen tasks. We then present an algorithm to solve this problem end-to-end through the use of an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.09767","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1710.09767","created_at":"2026-05-18T00:31:56.519789+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.09767v1","created_at":"2026-05-18T00:31:56.519789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.09767","created_at":"2026-05-18T00:31:56.519789+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMZO4XRSZ7SL","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMZO4XRSZ7SLHLBX","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMZO4XRS","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"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":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX","json":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX.json","graph_json":"https://pith.science/api/pith-number/QMZO4XRSZ7SLHLBXKP4JBPPKPX/graph.json","events_json":"https://pith.science/api/pith-number/QMZO4XRSZ7SLHLBXKP4JBPPKPX/events.json","paper":"https://pith.science/paper/QMZO4XRS"},"agent_actions":{"view_html":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX","download_json":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX.json","view_paper":"https://pith.science/paper/QMZO4XRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.09767&json=true","fetch_graph":"https://pith.science/api/pith-number/QMZO4XRSZ7SLHLBXKP4JBPPKPX/graph.json","fetch_events":"https://pith.science/api/pith-number/QMZO4XRSZ7SLHLBXKP4JBPPKPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX/action/storage_attestation","attest_author":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX/action/author_attestation","sign_citation":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX/action/citation_signature","submit_replication":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX/action/replication_record"}},"created_at":"2026-05-18T00:31:56.519789+00:00","updated_at":"2026-05-18T00:31:56.519789+00:00"}