{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DYZZ73AT3TGR6U7TQSVIBGHPRD","short_pith_number":"pith:DYZZ73AT","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"},"canonical_sha256":"1e339fec13dccd1f53f384aa8098ef88fa830eeb68a062e91c20dbcb149a9db9","source":{"kind":"arxiv","id":"2306.00867","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00867","created_at":"2026-07-05T08:19:34Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00867v1","created_at":"2026-07-05T08:19:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00867","created_at":"2026-07-05T08:19:34Z"},{"alias_kind":"pith_short_12","alias_value":"DYZZ73AT3TGR","created_at":"2026-07-05T08:19:34Z"},{"alias_kind":"pith_short_16","alias_value":"DYZZ73AT3TGR6U7T","created_at":"2026-07-05T08:19:34Z"},{"alias_kind":"pith_short_8","alias_value":"DYZZ73AT","created_at":"2026-07-05T08:19:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DYZZ73AT3TGR6U7TQSVIBGHPRD","target":"record","payload":{"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"},"canonical_sha256":"1e339fec13dccd1f53f384aa8098ef88fa830eeb68a062e91c20dbcb149a9db9","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"},"source_kind":"arxiv","source_id":"2306.00867","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:19:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TW9uDKV+ZAH/bNGU4X0RMl4C0lwuHWtsGN3TdiMJ74jH4a2DwblungMvQgyI/vNQ6wZ99aj34O0hYu2iXMLvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:32:33.068185Z"},"content_sha256":"040a6174d01f9c57173963d82e142712a6da56b269f8508aa2e3bbb5d3360e5c","schema_version":"1.0","event_id":"sha256:040a6174d01f9c57173963d82e142712a6da56b269f8508aa2e3bbb5d3360e5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DYZZ73AT3TGR6U7TQSVIBGHPRD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:19:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1jOshCHilO1k5sYv0pdhcy/cRbyKIW1GG5sV54EcPOe96NYJX+XYbzLBnW1FGfoSm1SOYLydlYuc8fCt7cmVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:32:33.069015Z"},"content_sha256":"1b1d6577286fd1942985e6eccc925528ba06e195dad21cf19fc9518dd12076b5","schema_version":"1.0","event_id":"sha256:1b1d6577286fd1942985e6eccc925528ba06e195dad21cf19fc9518dd12076b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD/bundle.json","state_url":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T17:32:33Z","links":{"resolver":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD","bundle":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD/bundle.json","state":"https://pith.science/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DYZZ73AT3TGR6U7TQSVIBGHPRD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DYZZ73AT3TGR6U7TQSVIBGHPRD","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":"f0ae6419f180bee6598381cbba222dc8aaec6dcd17ba5182f8125932c0b51e64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T16:24:40Z","title_canon_sha256":"3ea256c18dad12d009cc122bb9fd49fb7fe52d03fa53d6531e2c8842b4e4e801"},"schema_version":"1.0","source":{"id":"2306.00867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00867","created_at":"2026-07-05T08:19:34Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00867v1","created_at":"2026-07-05T08:19:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00867","created_at":"2026-07-05T08:19:34Z"},{"alias_kind":"pith_short_12","alias_value":"DYZZ73AT3TGR","created_at":"2026-07-05T08:19:34Z"},{"alias_kind":"pith_short_16","alias_value":"DYZZ73AT3TGR6U7T","created_at":"2026-07-05T08:19:34Z"},{"alias_kind":"pith_short_8","alias_value":"DYZZ73AT","created_at":"2026-07-05T08:19:34Z"}],"graph_snapshots":[{"event_id":"sha256:1b1d6577286fd1942985e6eccc925528ba06e195dad21cf19fc9518dd12076b5","target":"graph","created_at":"2026-07-05T08:19:34Z","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/2306.00867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Bobak Hashemi, Lucas Lehnert, Olivier Delalleau, Rohan Chitnis, Urun Dogan, Yingchen Xu, Zheqing Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T16:24:40Z","title":"IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00867","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":"sha256:040a6174d01f9c57173963d82e142712a6da56b269f8508aa2e3bbb5d3360e5c","target":"record","created_at":"2026-07-05T08:19:34Z","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":"f0ae6419f180bee6598381cbba222dc8aaec6dcd17ba5182f8125932c0b51e64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T16:24:40Z","title_canon_sha256":"3ea256c18dad12d009cc122bb9fd49fb7fe52d03fa53d6531e2c8842b4e4e801"},"schema_version":"1.0","source":{"id":"2306.00867","kind":"arxiv","version":1}},"canonical_sha256":"1e339fec13dccd1f53f384aa8098ef88fa830eeb68a062e91c20dbcb149a9db9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e339fec13dccd1f53f384aa8098ef88fa830eeb68a062e91c20dbcb149a9db9","first_computed_at":"2026-07-05T08:19:34.926800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:34.926800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n51tirvFtcXGC94fott31J9irwYReQzo9wk5cGrlrcaOheg6dusbJtXoFQk+AZ1YHiQt9OY2vprQx1QjY6vNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:34.927764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:040a6174d01f9c57173963d82e142712a6da56b269f8508aa2e3bbb5d3360e5c","sha256:1b1d6577286fd1942985e6eccc925528ba06e195dad21cf19fc9518dd12076b5"],"state_sha256":"854b16e091bf4ac7da468778deb5dcf6dcf24f077c57fbdbfcaea8a0f6cf20f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CIeAYw8dckE7MDZXlG+UpxplICPlq3ZGWUXh61igCzEoFFse27tqMsF248XIVYYVxJMb5uKjRxYoK2viN9fGCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:32:33.074379Z","bundle_sha256":"f2489fdb3bc1a67031c985abe3817f988a77deaaa3cc2e9934249a4be4b6671a"}}