{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:U4JHLDNAPLR3O4CIXDKATKJHOR","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":"c88c30956c7597a6bce97cba7cd2e2f6b1e92ad7b336ecece2ddd677a0c255f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-20T02:50:20Z","title_canon_sha256":"953edf0e60dd437aec7fc1e5ae6d4b730b2376f735ee070d06063b7084dcdec8"},"schema_version":"1.0","source":{"id":"1712.07294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.07294","created_at":"2026-05-18T00:27:34Z"},{"alias_kind":"arxiv_version","alias_value":"1712.07294v1","created_at":"2026-05-18T00:27:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07294","created_at":"2026-05-18T00:27:34Z"},{"alias_kind":"pith_short_12","alias_value":"U4JHLDNAPLR3","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"U4JHLDNAPLR3O4CI","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"U4JHLDNA","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:afb33502b61d319767502c9b8f70a5e20f2141cbd4d55c3509b82debb99967d5","target":"graph","created_at":"2026-05-18T00:27:34Z","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"},"paper":{"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 ","authors_text":"Caiming Xiong, Richard Socher, Tianmin Shu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-20T02:50:20Z","title":"Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.07294","kind":"arxiv","version":1},"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:ae772c8b806d7e21ef14d1b9e51acf232bc2337eed40db9f379a98ea796211a2","target":"record","created_at":"2026-05-18T00:27:34Z","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":"c88c30956c7597a6bce97cba7cd2e2f6b1e92ad7b336ecece2ddd677a0c255f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-20T02:50:20Z","title_canon_sha256":"953edf0e60dd437aec7fc1e5ae6d4b730b2376f735ee070d06063b7084dcdec8"},"schema_version":"1.0","source":{"id":"1712.07294","kind":"arxiv","version":1}},"canonical_sha256":"a712758da07ae3b77048b8d409a9277474f8c734c7242bc880da7a94dccf2aa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a712758da07ae3b77048b8d409a9277474f8c734c7242bc880da7a94dccf2aa2","first_computed_at":"2026-05-18T00:27:34.947916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:34.947916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4xS4UYWBYyhWf8gGpHkw3nmRKM8YHnAzAFvddQMchg3l5J9yybLbEY0oHSMuAhuhpxo4M6N1m6P8yRJ4ie9KCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:34.948543Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.07294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae772c8b806d7e21ef14d1b9e51acf232bc2337eed40db9f379a98ea796211a2","sha256:afb33502b61d319767502c9b8f70a5e20f2141cbd4d55c3509b82debb99967d5"],"state_sha256":"0f8828a54917080da7a0f7a61419de0a8784d535614af0f40f950033aa7ddab1"}