{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:U4JHLDNAPLR3O4CIXDKATKJHOR","short_pith_number":"pith:U4JHLDNA","schema_version":"1.0","canonical_sha256":"a712758da07ae3b77048b8d409a9277474f8c734c7242bc880da7a94dccf2aa2","source":{"kind":"arxiv","id":"1712.07294","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Caiming Xiong, Richard Socher, Tianmin Shu","submitted_at":"2017-12-20T02:50:20Z","abstract_excerpt":"Learning policies for complex tasks that require multiple different skills is a major challenge in reinforcement learning (RL). It is also a requirement for its deployment in real-world scenarios. This paper proposes a novel framework for efficient multi-task reinforcement learning. Our framework trains agents to employ hierarchical policies that decide when to use a previously learned policy and when to learn a new skill. This enables agents to continually acquire new skills during different stages of training. Each learned task corresponds to a human language description. Because agents can "},"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":"1712.07294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-20T02:50:20Z","cross_cats_sorted":[],"title_canon_sha256":"953edf0e60dd437aec7fc1e5ae6d4b730b2376f735ee070d06063b7084dcdec8","abstract_canon_sha256":"c88c30956c7597a6bce97cba7cd2e2f6b1e92ad7b336ecece2ddd677a0c255f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:34.948543Z","signature_b64":"4xS4UYWBYyhWf8gGpHkw3nmRKM8YHnAzAFvddQMchg3l5J9yybLbEY0oHSMuAhuhpxo4M6N1m6P8yRJ4ie9KCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a712758da07ae3b77048b8d409a9277474f8c734c7242bc880da7a94dccf2aa2","last_reissued_at":"2026-05-18T00:27:34.947916Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:34.947916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Caiming Xiong, Richard Socher, Tianmin Shu","submitted_at":"2017-12-20T02:50:20Z","abstract_excerpt":"Learning policies for complex tasks that require multiple different skills is a major challenge in reinforcement learning (RL). It is also a requirement for its deployment in real-world scenarios. This paper proposes a novel framework for efficient multi-task reinforcement learning. Our framework trains agents to employ hierarchical policies that decide when to use a previously learned policy and when to learn a new skill. This enables agents to continually acquire new skills during different stages of training. Each learned task corresponds to a human language description. Because agents can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.07294","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":"1712.07294","created_at":"2026-05-18T00:27:34.948024+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.07294v1","created_at":"2026-05-18T00:27:34.948024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07294","created_at":"2026-05-18T00:27:34.948024+00:00"},{"alias_kind":"pith_short_12","alias_value":"U4JHLDNAPLR3","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"U4JHLDNAPLR3O4CI","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"U4JHLDNA","created_at":"2026-05-18T12:31:46.661854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.08584","citing_title":"CraftAssist: A Framework for Dialogue-enabled Interactive Agents","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09273","citing_title":"Why Build an Assistant in Minecraft?","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2408.00724","citing_title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","ref_index":100,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U4JHLDNAPLR3O4CIXDKATKJHOR","json":"https://pith.science/pith/U4JHLDNAPLR3O4CIXDKATKJHOR.json","graph_json":"https://pith.science/api/pith-number/U4JHLDNAPLR3O4CIXDKATKJHOR/graph.json","events_json":"https://pith.science/api/pith-number/U4JHLDNAPLR3O4CIXDKATKJHOR/events.json","paper":"https://pith.science/paper/U4JHLDNA"},"agent_actions":{"view_html":"https://pith.science/pith/U4JHLDNAPLR3O4CIXDKATKJHOR","download_json":"https://pith.science/pith/U4JHLDNAPLR3O4CIXDKATKJHOR.json","view_paper":"https://pith.science/paper/U4JHLDNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.07294&json=true","fetch_graph":"https://pith.science/api/pith-number/U4JHLDNAPLR3O4CIXDKATKJHOR/graph.json","fetch_events":"https://pith.science/api/pith-number/U4JHLDNAPLR3O4CIXDKATKJHOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U4JHLDNAPLR3O4CIXDKATKJHOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U4JHLDNAPLR3O4CIXDKATKJHOR/action/storage_attestation","attest_author":"https://pith.science/pith/U4JHLDNAPLR3O4CIXDKATKJHOR/action/author_attestation","sign_citation":"https://pith.science/pith/U4JHLDNAPLR3O4CIXDKATKJHOR/action/citation_signature","submit_replication":"https://pith.science/pith/U4JHLDNAPLR3O4CIXDKATKJHOR/action/replication_record"}},"created_at":"2026-05-18T00:27:34.948024+00:00","updated_at":"2026-05-18T00:27:34.948024+00:00"}