{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H4XATGTVMYUP3AROSLT25YKKN5","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":"e4d4b886bed57abb6f0e937c113c10e222241c87c1ba9ddd8172450fcc541274","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T03:32:13Z","title_canon_sha256":"4c49914f3b21e39b1e6a3c22564cc2ff0f3a48ce66b7a08033deee7fcac9faae"},"schema_version":"1.0","source":{"id":"2311.00267","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00267","created_at":"2026-07-05T07:07:44Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00267v1","created_at":"2026-07-05T07:07:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00267","created_at":"2026-07-05T07:07:44Z"},{"alias_kind":"pith_short_12","alias_value":"H4XATGTVMYUP","created_at":"2026-07-05T07:07:44Z"},{"alias_kind":"pith_short_16","alias_value":"H4XATGTVMYUP3ARO","created_at":"2026-07-05T07:07:44Z"},{"alias_kind":"pith_short_8","alias_value":"H4XATGTV","created_at":"2026-07-05T07:07:44Z"}],"graph_snapshots":[{"event_id":"sha256:16c9a524f304647673b520f7e591c3ef0395100f870f4c270eebfedae35c3126","target":"graph","created_at":"2026-07-05T07:07:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.00267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decision Transformer (DT) is an innovative algorithm leveraging recent advances of the transformer architecture in reinforcement learning (RL). However, a notable limitation of DT is its reliance on recalling trajectories from datasets, losing the capability to seamlessly stitch sub-optimal trajectories together. In this work we introduce a general sequence modeling framework for studying sequential decision making through the lens of Hierarchical RL. At the time of making decisions, a high-level policy first proposes an ideal prompt for the current state, a low-level policy subsequently gener","authors_text":"Chenjun Xiao, Hebin Liang, Jianye Hao, Yi Ma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T03:32:13Z","title":"Rethinking Decision Transformer via Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00267","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":"sha256:9f19b34d0fab05902abf822b6dd5ab05e3582db722cb59cc27c0e4954ab9c89b","target":"record","created_at":"2026-07-05T07:07:44Z","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":"e4d4b886bed57abb6f0e937c113c10e222241c87c1ba9ddd8172450fcc541274","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T03:32:13Z","title_canon_sha256":"4c49914f3b21e39b1e6a3c22564cc2ff0f3a48ce66b7a08033deee7fcac9faae"},"schema_version":"1.0","source":{"id":"2311.00267","kind":"arxiv","version":1}},"canonical_sha256":"3f2e099a756628fd822e92e7aee14a6f67319230c017f0d21687bebc14afb56b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f2e099a756628fd822e92e7aee14a6f67319230c017f0d21687bebc14afb56b","first_computed_at":"2026-07-05T07:07:44.717287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:44.717287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nmPjFx9fcfvgKePZfUcHZa+TlH7vZ6rZGlkrn+qaOsDmGcfLfGGzMJsYGoiMMvB+MY6NbCTDj3+l8wVbt60KDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:44.717678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00267","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f19b34d0fab05902abf822b6dd5ab05e3582db722cb59cc27c0e4954ab9c89b","sha256:16c9a524f304647673b520f7e591c3ef0395100f870f4c270eebfedae35c3126"],"state_sha256":"e8a5fd7a2ab685849f5147969f7df89163df762bd1e9d815ce7d4bcd36fffb8d"}