{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:EVB4BMBY6Z475X55TF74K563RN","short_pith_number":"pith:EVB4BMBY","schema_version":"1.0","canonical_sha256":"2543c0b038f679fedfbd997fc577db8b7b17a5925c03979066183ab32d92cd3a","source":{"kind":"arxiv","id":"1711.00129","version":2},"attestation_state":"computed","paper":{"title":"Automata-Guided Hierarchical Reinforcement Learning for Skill Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Calin Belta, Xiao Li, Yao Ma","submitted_at":"2017-10-31T22:21:02Z","abstract_excerpt":"Skills learned through (deep) reinforcement learning often generalizes poorly across domains and re-training is necessary when presented with a new task. We present a framework that combines techniques in \\textit{formal methods} with \\textit{reinforcement learning} (RL). The methods we provide allows for convenient specification of tasks with logical expressions, learns hierarchical policies (meta-controller and low-level controllers) with well-defined intrinsic rewards, and construct new skills from existing ones with little to no additional exploration. We evaluate the proposed methods in a "},"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":"1711.00129","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-31T22:21:02Z","cross_cats_sorted":[],"title_canon_sha256":"8ba76dcdc5aa31a55f45df25aa17d199be351babb9f01e49ad3069436e0883bc","abstract_canon_sha256":"4276ff35af4927de3d912249a4d331dd7bb56513ba37c48ed555f374ac2f3c5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:37.133446Z","signature_b64":"tt2xstca9GPrE4xQUPGu2NYX/V8h6rYP3swO8hGy1dRVnSAr/f7C6vyIVkDgJ+OI9HOJa95U1ztSu9wz1LSjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2543c0b038f679fedfbd997fc577db8b7b17a5925c03979066183ab32d92cd3a","last_reissued_at":"2026-05-18T00:15:37.132911Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:37.132911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automata-Guided Hierarchical Reinforcement Learning for Skill Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Calin Belta, Xiao Li, Yao Ma","submitted_at":"2017-10-31T22:21:02Z","abstract_excerpt":"Skills learned through (deep) reinforcement learning often generalizes poorly across domains and re-training is necessary when presented with a new task. We present a framework that combines techniques in \\textit{formal methods} with \\textit{reinforcement learning} (RL). The methods we provide allows for convenient specification of tasks with logical expressions, learns hierarchical policies (meta-controller and low-level controllers) with well-defined intrinsic rewards, and construct new skills from existing ones with little to no additional exploration. We evaluate the proposed methods in a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00129","kind":"arxiv","version":2},"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":"1711.00129","created_at":"2026-05-18T00:15:37.132989+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.00129v2","created_at":"2026-05-18T00:15:37.132989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00129","created_at":"2026-05-18T00:15:37.132989+00:00"},{"alias_kind":"pith_short_12","alias_value":"EVB4BMBY6Z47","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"EVB4BMBY6Z475X55","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"EVB4BMBY","created_at":"2026-05-18T12:31:12.930513+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/EVB4BMBY6Z475X55TF74K563RN","json":"https://pith.science/pith/EVB4BMBY6Z475X55TF74K563RN.json","graph_json":"https://pith.science/api/pith-number/EVB4BMBY6Z475X55TF74K563RN/graph.json","events_json":"https://pith.science/api/pith-number/EVB4BMBY6Z475X55TF74K563RN/events.json","paper":"https://pith.science/paper/EVB4BMBY"},"agent_actions":{"view_html":"https://pith.science/pith/EVB4BMBY6Z475X55TF74K563RN","download_json":"https://pith.science/pith/EVB4BMBY6Z475X55TF74K563RN.json","view_paper":"https://pith.science/paper/EVB4BMBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.00129&json=true","fetch_graph":"https://pith.science/api/pith-number/EVB4BMBY6Z475X55TF74K563RN/graph.json","fetch_events":"https://pith.science/api/pith-number/EVB4BMBY6Z475X55TF74K563RN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EVB4BMBY6Z475X55TF74K563RN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EVB4BMBY6Z475X55TF74K563RN/action/storage_attestation","attest_author":"https://pith.science/pith/EVB4BMBY6Z475X55TF74K563RN/action/author_attestation","sign_citation":"https://pith.science/pith/EVB4BMBY6Z475X55TF74K563RN/action/citation_signature","submit_replication":"https://pith.science/pith/EVB4BMBY6Z475X55TF74K563RN/action/replication_record"}},"created_at":"2026-05-18T00:15:37.132989+00:00","updated_at":"2026-05-18T00:15:37.132989+00:00"}