{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3YBVZDTTEZOUODP73NAQ5HPYHR","short_pith_number":"pith:3YBVZDTT","schema_version":"1.0","canonical_sha256":"de035c8e73265d470dffdb410e9df83c58cdb614fc5310314508a658caf8d5fe","source":{"kind":"arxiv","id":"2206.04114","version":1},"attestation_state":"computed","paper":{"title":"Deep Hierarchical Planning from Pixels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","stat.ML"],"primary_cat":"cs.AI","authors_text":"Danijar Hafner, Ian Fischer, Kuang-Huei Lee, Pieter Abbeel","submitted_at":"2022-06-08T18:20:15Z","abstract_excerpt":"Intelligent agents need to select long sequences of actions to solve complex tasks. While humans easily break down tasks into subgoals and reach them through millions of muscle commands, current artificial intelligence is limited to tasks with horizons of a few hundred decisions, despite large compute budgets. Research on hierarchical reinforcement learning aims to overcome this limitation but has proven to be challenging, current methods rely on manually specified goal spaces or subtasks, and no general solution exists. We introduce Director, a practical method for learning hierarchical behav"},"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":"2206.04114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-06-08T18:20:15Z","cross_cats_sorted":["cs.LG","cs.RO","stat.ML"],"title_canon_sha256":"163c2008b21b8571a6610c63072d7de0fe8b6ee292ee9ef3aab609c611e56986","abstract_canon_sha256":"fabe2bb06d7c98cfe1ccc10be277a9e9bfb952ac3ec3f948810d1da8e609d382"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:23.035963Z","signature_b64":"IPf0nv+BRB+29j+glF3nXjnx/5G3u7ZUcqgXbTL0pBW4LtiVBfAY82HU/gQhBtlkc7oZB+Tw3rx4Usp2Nw14AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de035c8e73265d470dffdb410e9df83c58cdb614fc5310314508a658caf8d5fe","last_reissued_at":"2026-07-05T04:30:23.035512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:23.035512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Hierarchical Planning from Pixels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","stat.ML"],"primary_cat":"cs.AI","authors_text":"Danijar Hafner, Ian Fischer, Kuang-Huei Lee, Pieter Abbeel","submitted_at":"2022-06-08T18:20:15Z","abstract_excerpt":"Intelligent agents need to select long sequences of actions to solve complex tasks. While humans easily break down tasks into subgoals and reach them through millions of muscle commands, current artificial intelligence is limited to tasks with horizons of a few hundred decisions, despite large compute budgets. Research on hierarchical reinforcement learning aims to overcome this limitation but has proven to be challenging, current methods rely on manually specified goal spaces or subtasks, and no general solution exists. We introduce Director, a practical method for learning hierarchical behav"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04114","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.04114/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2206.04114","created_at":"2026-07-05T04:30:23.035582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04114v1","created_at":"2026-07-05T04:30:23.035582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04114","created_at":"2026-07-05T04:30:23.035582+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YBVZDTTEZOU","created_at":"2026-07-05T04:30:23.035582+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YBVZDTTEZOUODP7","created_at":"2026-07-05T04:30:23.035582+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YBVZDTT","created_at":"2026-07-05T04:30:23.035582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.08751","citing_title":"Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":300,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05608","citing_title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10333","citing_title":"Zero-shot World Models Are Developmentally Efficient Learners","ref_index":104,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YBVZDTTEZOUODP73NAQ5HPYHR","json":"https://pith.science/pith/3YBVZDTTEZOUODP73NAQ5HPYHR.json","graph_json":"https://pith.science/api/pith-number/3YBVZDTTEZOUODP73NAQ5HPYHR/graph.json","events_json":"https://pith.science/api/pith-number/3YBVZDTTEZOUODP73NAQ5HPYHR/events.json","paper":"https://pith.science/paper/3YBVZDTT"},"agent_actions":{"view_html":"https://pith.science/pith/3YBVZDTTEZOUODP73NAQ5HPYHR","download_json":"https://pith.science/pith/3YBVZDTTEZOUODP73NAQ5HPYHR.json","view_paper":"https://pith.science/paper/3YBVZDTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04114&json=true","fetch_graph":"https://pith.science/api/pith-number/3YBVZDTTEZOUODP73NAQ5HPYHR/graph.json","fetch_events":"https://pith.science/api/pith-number/3YBVZDTTEZOUODP73NAQ5HPYHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YBVZDTTEZOUODP73NAQ5HPYHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YBVZDTTEZOUODP73NAQ5HPYHR/action/storage_attestation","attest_author":"https://pith.science/pith/3YBVZDTTEZOUODP73NAQ5HPYHR/action/author_attestation","sign_citation":"https://pith.science/pith/3YBVZDTTEZOUODP73NAQ5HPYHR/action/citation_signature","submit_replication":"https://pith.science/pith/3YBVZDTTEZOUODP73NAQ5HPYHR/action/replication_record"}},"created_at":"2026-07-05T04:30:23.035582+00:00","updated_at":"2026-07-05T04:30:23.035582+00:00"}