{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:55LPHDZ2ABDRX5BYU3DHX7D2PF","short_pith_number":"pith:55LPHDZ2","schema_version":"1.0","canonical_sha256":"ef56f38f3a00471bf438a6c67bfc7a797bfa4042ad224a6c9f865d8326b0c726","source":{"kind":"arxiv","id":"1711.11289","version":1},"attestation_state":"computed","paper":{"title":"Learning to Compose Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Charles Isbell, Farhan Tejani, Himanshu Sahni, Saurabh Kumar","submitted_at":"2017-11-30T09:47:28Z","abstract_excerpt":"We present a differentiable framework capable of learning a wide variety of compositions of simple policies that we call skills. By recursively composing skills with themselves, we can create hierarchies that display complex behavior. Skill networks are trained to generate skill-state embeddings that are provided as inputs to a trainable composition function, which in turn outputs a policy for the overall task. Our experiments on an environment consisting of multiple collect and evade tasks show that this architecture is able to quickly build complex skills from simpler ones. Furthermore, the "},"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":"1711.11289","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-30T09:47:28Z","cross_cats_sorted":[],"title_canon_sha256":"23beed96a983115b4d44b593f71a0b568485aa6fcafa641692249c43e66286c5","abstract_canon_sha256":"f9e622e06313f538adef88a4a4e4a94ad64a93359c0b2de504ca91e8e52df2fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:11.943810Z","signature_b64":"HA1j0bJFGtjdToFVFVFSzyyYlLnI60XVEVzd4FHYcfyLE9LxxsEH+Gdx8mekGVa2rxkQ15RGRUnias+j+A0tAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef56f38f3a00471bf438a6c67bfc7a797bfa4042ad224a6c9f865d8326b0c726","last_reissued_at":"2026-05-18T00:29:11.943138Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:11.943138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Compose Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Charles Isbell, Farhan Tejani, Himanshu Sahni, Saurabh Kumar","submitted_at":"2017-11-30T09:47:28Z","abstract_excerpt":"We present a differentiable framework capable of learning a wide variety of compositions of simple policies that we call skills. By recursively composing skills with themselves, we can create hierarchies that display complex behavior. Skill networks are trained to generate skill-state embeddings that are provided as inputs to a trainable composition function, which in turn outputs a policy for the overall task. Our experiments on an environment consisting of multiple collect and evade tasks show that this architecture is able to quickly build complex skills from simpler ones. Furthermore, the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11289","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":"1711.11289","created_at":"2026-05-18T00:29:11.943238+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.11289v1","created_at":"2026-05-18T00:29:11.943238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11289","created_at":"2026-05-18T00:29:11.943238+00:00"},{"alias_kind":"pith_short_12","alias_value":"55LPHDZ2ABDR","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"55LPHDZ2ABDRX5BY","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"55LPHDZ2","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55LPHDZ2ABDRX5BYU3DHX7D2PF","json":"https://pith.science/pith/55LPHDZ2ABDRX5BYU3DHX7D2PF.json","graph_json":"https://pith.science/api/pith-number/55LPHDZ2ABDRX5BYU3DHX7D2PF/graph.json","events_json":"https://pith.science/api/pith-number/55LPHDZ2ABDRX5BYU3DHX7D2PF/events.json","paper":"https://pith.science/paper/55LPHDZ2"},"agent_actions":{"view_html":"https://pith.science/pith/55LPHDZ2ABDRX5BYU3DHX7D2PF","download_json":"https://pith.science/pith/55LPHDZ2ABDRX5BYU3DHX7D2PF.json","view_paper":"https://pith.science/paper/55LPHDZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.11289&json=true","fetch_graph":"https://pith.science/api/pith-number/55LPHDZ2ABDRX5BYU3DHX7D2PF/graph.json","fetch_events":"https://pith.science/api/pith-number/55LPHDZ2ABDRX5BYU3DHX7D2PF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55LPHDZ2ABDRX5BYU3DHX7D2PF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55LPHDZ2ABDRX5BYU3DHX7D2PF/action/storage_attestation","attest_author":"https://pith.science/pith/55LPHDZ2ABDRX5BYU3DHX7D2PF/action/author_attestation","sign_citation":"https://pith.science/pith/55LPHDZ2ABDRX5BYU3DHX7D2PF/action/citation_signature","submit_replication":"https://pith.science/pith/55LPHDZ2ABDRX5BYU3DHX7D2PF/action/replication_record"}},"created_at":"2026-05-18T00:29:11.943238+00:00","updated_at":"2026-05-18T00:29:11.943238+00:00"}