{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DYZZ73AT3TGR6U7TQSVIBGHPRD","short_pith_number":"pith:DYZZ73AT","schema_version":"1.0","canonical_sha256":"1e339fec13dccd1f53f384aa8098ef88fa830eeb68a062e91c20dbcb149a9db9","source":{"kind":"arxiv","id":"2306.00867","version":1},"attestation_state":"computed","paper":{"title":"IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bobak Hashemi, Lucas Lehnert, Olivier Delalleau, Rohan Chitnis, Urun Dogan, Yingchen Xu, Zheqing Zhu","submitted_at":"2023-06-01T16:24:40Z","abstract_excerpt":"Model-based reinforcement learning (RL) has shown great promise due to its sample efficiency, but still struggles with long-horizon sparse-reward tasks, especially in offline settings where the agent learns from a fixed dataset. We hypothesize that model-based RL agents struggle in these environments due to a lack of long-term planning capabilities, and that planning in a temporally abstract model of the environment can alleviate this issue. In this paper, we make two key contributions: 1) we introduce an offline model-based RL algorithm, IQL-TD-MPC, that extends the state-of-the-art Temporal "},"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":"2306.00867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T16:24:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3ea256c18dad12d009cc122bb9fd49fb7fe52d03fa53d6531e2c8842b4e4e801","abstract_canon_sha256":"f0ae6419f180bee6598381cbba222dc8aaec6dcd17ba5182f8125932c0b51e64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:34.927764Z","signature_b64":"n51tirvFtcXGC94fott31J9irwYReQzo9wk5cGrlrcaOheg6dusbJtXoFQk+AZ1YHiQt9OY2vprQx1QjY6vNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e339fec13dccd1f53f384aa8098ef88fa830eeb68a062e91c20dbcb149a9db9","last_reissued_at":"2026-07-05T08:19:34.926800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:34.926800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bobak Hashemi, Lucas Lehnert, Olivier Delalleau, Rohan Chitnis, Urun Dogan, Yingchen Xu, Zheqing Zhu","submitted_at":"2023-06-01T16:24:40Z","abstract_excerpt":"Model-based reinforcement learning (RL) has shown great promise due to its sample efficiency, but still struggles with long-horizon sparse-reward tasks, especially in offline settings where the agent learns from a fixed dataset. We hypothesize that model-based RL agents struggle in these environments due to a lack of long-term planning capabilities, and that planning in a temporally abstract model of the environment can alleviate this issue. In this paper, we make two key contributions: 1) we introduce an offline model-based RL algorithm, IQL-TD-MPC, that extends the state-of-the-art Temporal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00867","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/2306.00867/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":"2306.00867","created_at":"2026-07-05T08:19:34.927149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00867v1","created_at":"2026-07-05T08:19:34.927149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00867","created_at":"2026-07-05T08:19:34.927149+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYZZ73AT3TGR","created_at":"2026-07-05T08:19:34.927149+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYZZ73AT3TGR6U7T","created_at":"2026-07-05T08:19:34.927149+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYZZ73AT","created_at":"2026-07-05T08:19:34.927149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.05907","citing_title":"EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2310.16828","citing_title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","ref_index":153,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD","json":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD.json","graph_json":"https://pith.science/api/pith-number/DYZZ73AT3TGR6U7TQSVIBGHPRD/graph.json","events_json":"https://pith.science/api/pith-number/DYZZ73AT3TGR6U7TQSVIBGHPRD/events.json","paper":"https://pith.science/paper/DYZZ73AT"},"agent_actions":{"view_html":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD","download_json":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD.json","view_paper":"https://pith.science/paper/DYZZ73AT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00867&json=true","fetch_graph":"https://pith.science/api/pith-number/DYZZ73AT3TGR6U7TQSVIBGHPRD/graph.json","fetch_events":"https://pith.science/api/pith-number/DYZZ73AT3TGR6U7TQSVIBGHPRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD/action/storage_attestation","attest_author":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD/action/author_attestation","sign_citation":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD/action/citation_signature","submit_replication":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD/action/replication_record"}},"created_at":"2026-07-05T08:19:34.927149+00:00","updated_at":"2026-07-05T08:19:34.927149+00:00"}