{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:O3OT7QL7VUXZEYDQNFBOFHDZ6N","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":"4dfe1919c80127d80c5165807cbf594294fb7dff6dfb97fc9f95385d080b3738","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-03-29T18:17:17Z","title_canon_sha256":"514a4c2540463dbcd83b9e9e01ff20c5865d4744476dc31e78f0fbbe133ff240"},"schema_version":"1.0","source":{"id":"1603.08869","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.08869","created_at":"2026-05-18T01:18:05Z"},{"alias_kind":"arxiv_version","alias_value":"1603.08869v1","created_at":"2026-05-18T01:18:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.08869","created_at":"2026-05-18T01:18:05Z"},{"alias_kind":"pith_short_12","alias_value":"O3OT7QL7VUXZ","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"O3OT7QL7VUXZEYDQ","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"O3OT7QL7","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:c107862643350a6231e17ee4ead7be4b21ac26c03d6fd58f195d9983cb5bc7a2","target":"graph","created_at":"2026-05-18T01:18:05Z","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":"Hierarchical Reinforcement Learning (HRL) exploits temporal abstraction to solve large Markov Decision Processes (MDP) and provide transferable subtask policies. In this paper, we introduce an off-policy HRL algorithm: Hierarchical Q-value Iteration (HQI). We show that it is possible to effectively learn recursive optimal policies for any valid hierarchical decomposition of the original MDP, given a fixed dataset collected from a flat stochastic behavioral policy. We first formally prove the convergence of the algorithm for tabular MDP. Then our experiments on the Taxi domain show that HQI con","authors_text":"Mohammad Gowayyed, Tiancheng Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-03-29T18:17:17Z","title":"Algorithms for Batch Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.08869","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":"sha256:09992cd7661f76856b2a6118372c5a09e88c571efde94bbc7d9030dc42b08b5f","target":"record","created_at":"2026-05-18T01:18:05Z","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":"4dfe1919c80127d80c5165807cbf594294fb7dff6dfb97fc9f95385d080b3738","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-03-29T18:17:17Z","title_canon_sha256":"514a4c2540463dbcd83b9e9e01ff20c5865d4744476dc31e78f0fbbe133ff240"},"schema_version":"1.0","source":{"id":"1603.08869","kind":"arxiv","version":1}},"canonical_sha256":"76dd3fc17fad2f9260706942e29c79f377e3ca769d3892cfdd21660dca62f753","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76dd3fc17fad2f9260706942e29c79f377e3ca769d3892cfdd21660dca62f753","first_computed_at":"2026-05-18T01:18:05.108442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:18:05.108442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5gyC5VBgXy9NxOxFfF0BXL4ziApdYrvH4xD2NlYIE9Y0Lq2AxkzC08A3Y+B/eFDoMd6G6zYY8LhdS/Ae6txUBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:18:05.109042Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.08869","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09992cd7661f76856b2a6118372c5a09e88c571efde94bbc7d9030dc42b08b5f","sha256:c107862643350a6231e17ee4ead7be4b21ac26c03d6fd58f195d9983cb5bc7a2"],"state_sha256":"ae32361bb921c04e6c2ae3ebf2e970b1b93a31c7be05fd091ac8175653d1d12b"}