{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EVB4BMBY6Z475X55TF74K563RN","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":"4276ff35af4927de3d912249a4d331dd7bb56513ba37c48ed555f374ac2f3c5e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-31T22:21:02Z","title_canon_sha256":"8ba76dcdc5aa31a55f45df25aa17d199be351babb9f01e49ad3069436e0883bc"},"schema_version":"1.0","source":{"id":"1711.00129","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00129","created_at":"2026-05-18T00:15:37Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00129v2","created_at":"2026-05-18T00:15:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00129","created_at":"2026-05-18T00:15:37Z"},{"alias_kind":"pith_short_12","alias_value":"EVB4BMBY6Z47","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EVB4BMBY6Z475X55","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EVB4BMBY","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:656b531507d2837bf120ebb0975ac2cab7ecacad0d6875b0a671c4e6257b073f","target":"graph","created_at":"2026-05-18T00:15:37Z","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":"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 ","authors_text":"Calin Belta, Xiao Li, Yao Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-31T22:21:02Z","title":"Automata-Guided Hierarchical Reinforcement Learning for Skill Composition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00129","kind":"arxiv","version":2},"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:dbbab731b355841b542cab91d01b7ad8e4449945d7d03219032f26d26382505f","target":"record","created_at":"2026-05-18T00:15:37Z","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":"4276ff35af4927de3d912249a4d331dd7bb56513ba37c48ed555f374ac2f3c5e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-31T22:21:02Z","title_canon_sha256":"8ba76dcdc5aa31a55f45df25aa17d199be351babb9f01e49ad3069436e0883bc"},"schema_version":"1.0","source":{"id":"1711.00129","kind":"arxiv","version":2}},"canonical_sha256":"2543c0b038f679fedfbd997fc577db8b7b17a5925c03979066183ab32d92cd3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2543c0b038f679fedfbd997fc577db8b7b17a5925c03979066183ab32d92cd3a","first_computed_at":"2026-05-18T00:15:37.132911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:37.132911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tt2xstca9GPrE4xQUPGu2NYX/V8h6rYP3swO8hGy1dRVnSAr/f7C6vyIVkDgJ+OI9HOJa95U1ztSu9wz1LSjBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:37.133446Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.00129","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbbab731b355841b542cab91d01b7ad8e4449945d7d03219032f26d26382505f","sha256:656b531507d2837bf120ebb0975ac2cab7ecacad0d6875b0a671c4e6257b073f"],"state_sha256":"dd4f076d5b8da0b71fdbcf88d9ef56c5c0ebd891d320f1f834590232ae869e28"}