{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UPZ3H3UBZV5GDDNBKR2HSAX6SM","short_pith_number":"pith:UPZ3H3UB","canonical_record":{"source":{"id":"2205.11790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2022-05-24T05:13:40Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"b472fbaf95d10af574afc8f1b8ebefda468a1270fa68ad2468b5de8804c7ab67","abstract_canon_sha256":"236f447c3dd3a3022a8bdcced816af92da87614e39c9119d0b7513ecf1711e39"},"schema_version":"1.0"},"canonical_sha256":"a3f3b3ee81cd7a618da154747902fe930e2021b4fc0e0866c306d82acf33b33a","source":{"kind":"arxiv","id":"2205.11790","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11790","created_at":"2026-07-05T04:26:08Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11790v1","created_at":"2026-07-05T04:26:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11790","created_at":"2026-07-05T04:26:08Z"},{"alias_kind":"pith_short_12","alias_value":"UPZ3H3UBZV5G","created_at":"2026-07-05T04:26:08Z"},{"alias_kind":"pith_short_16","alias_value":"UPZ3H3UBZV5GDDNB","created_at":"2026-07-05T04:26:08Z"},{"alias_kind":"pith_short_8","alias_value":"UPZ3H3UB","created_at":"2026-07-05T04:26:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UPZ3H3UBZV5GDDNBKR2HSAX6SM","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2022-05-24T05:13:40Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"b472fbaf95d10af574afc8f1b8ebefda468a1270fa68ad2468b5de8804c7ab67","abstract_canon_sha256":"236f447c3dd3a3022a8bdcced816af92da87614e39c9119d0b7513ecf1711e39"},"schema_version":"1.0"},"canonical_sha256":"a3f3b3ee81cd7a618da154747902fe930e2021b4fc0e0866c306d82acf33b33a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:08.372109Z","signature_b64":"SdDpVSZ57KqobGokXjgUfgTkHsq2usS2eshPUrXyQLXLYPJWqbFIbvlg4xzm1qlbIRDJohh4ZK511/lsLRwyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3f3b3ee81cd7a618da154747902fe930e2021b4fc0e0866c306d82acf33b33a","last_reissued_at":"2026-07-05T04:26:08.371674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:08.371674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11790","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":"2026-07-05T04:26:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WxORsjUUb7gECBpIeb0JZo533R9LR1QPQ4243gingNaDIovyFy4LmPeKVBZ0YHflZbacswA66WffIBwfInJUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:07:45.113540Z"},"content_sha256":"5fa4dcdcd6cd3580055d5695f74de27236311d00481fc2216caaf78bd6ec1e9d","schema_version":"1.0","event_id":"sha256:5fa4dcdcd6cd3580055d5695f74de27236311d00481fc2216caaf78bd6ec1e9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UPZ3H3UBZV5GDDNBKR2HSAX6SM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Chen Tang, Jinning Li, Masayoshi Tomizuka, Wei Zhan","submitted_at":"2022-05-24T05:13:40Z","abstract_excerpt":"Offline Reinforcement learning (RL) has shown potent in many safe-critical tasks in robotics where exploration is risky and expensive. However, it still struggles to acquire skills in temporally extended tasks. In this paper, we study the problem of offline RL for temporally extended tasks. We propose a hierarchical planning framework, consisting of a low-level goal-conditioned RL policy and a high-level goal planner. The low-level policy is trained via offline RL. We improve the offline training to deal with out-of-distribution goals by a perturbed goal sampling process. The high-level planne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11790","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/2205.11790/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":"2026-07-05T04:26:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gsY4iXQbSXAixOJyIszrNZVf85WJE0xSYCwbsI3qfXX9FipiZloPdheDnrSeqFf5dhUEzm0uc6EEbAw3VDgfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:07:45.114315Z"},"content_sha256":"d95f1708541401283768979afde81107bfa08f500ac62b2cfc92f444d5c4f5dd","schema_version":"1.0","event_id":"sha256:d95f1708541401283768979afde81107bfa08f500ac62b2cfc92f444d5c4f5dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UPZ3H3UBZV5GDDNBKR2HSAX6SM/bundle.json","state_url":"https://pith.science/pith/UPZ3H3UBZV5GDDNBKR2HSAX6SM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UPZ3H3UBZV5GDDNBKR2HSAX6SM/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":"2026-08-18T15:07:45Z","links":{"resolver":"https://pith.science/pith/UPZ3H3UBZV5GDDNBKR2HSAX6SM","bundle":"https://pith.science/pith/UPZ3H3UBZV5GDDNBKR2HSAX6SM/bundle.json","state":"https://pith.science/pith/UPZ3H3UBZV5GDDNBKR2HSAX6SM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UPZ3H3UBZV5GDDNBKR2HSAX6SM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UPZ3H3UBZV5GDDNBKR2HSAX6SM","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":"236f447c3dd3a3022a8bdcced816af92da87614e39c9119d0b7513ecf1711e39","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2022-05-24T05:13:40Z","title_canon_sha256":"b472fbaf95d10af574afc8f1b8ebefda468a1270fa68ad2468b5de8804c7ab67"},"schema_version":"1.0","source":{"id":"2205.11790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11790","created_at":"2026-07-05T04:26:08Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11790v1","created_at":"2026-07-05T04:26:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11790","created_at":"2026-07-05T04:26:08Z"},{"alias_kind":"pith_short_12","alias_value":"UPZ3H3UBZV5G","created_at":"2026-07-05T04:26:08Z"},{"alias_kind":"pith_short_16","alias_value":"UPZ3H3UBZV5GDDNB","created_at":"2026-07-05T04:26:08Z"},{"alias_kind":"pith_short_8","alias_value":"UPZ3H3UB","created_at":"2026-07-05T04:26:08Z"}],"graph_snapshots":[{"event_id":"sha256:d95f1708541401283768979afde81107bfa08f500ac62b2cfc92f444d5c4f5dd","target":"graph","created_at":"2026-07-05T04:26:08Z","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/2205.11790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline Reinforcement learning (RL) has shown potent in many safe-critical tasks in robotics where exploration is risky and expensive. However, it still struggles to acquire skills in temporally extended tasks. In this paper, we study the problem of offline RL for temporally extended tasks. We propose a hierarchical planning framework, consisting of a low-level goal-conditioned RL policy and a high-level goal planner. The low-level policy is trained via offline RL. We improve the offline training to deal with out-of-distribution goals by a perturbed goal sampling process. The high-level planne","authors_text":"Chen Tang, Jinning Li, Masayoshi Tomizuka, Wei Zhan","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2022-05-24T05:13:40Z","title":"Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11790","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":"sha256:5fa4dcdcd6cd3580055d5695f74de27236311d00481fc2216caaf78bd6ec1e9d","target":"record","created_at":"2026-07-05T04:26:08Z","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":"236f447c3dd3a3022a8bdcced816af92da87614e39c9119d0b7513ecf1711e39","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2022-05-24T05:13:40Z","title_canon_sha256":"b472fbaf95d10af574afc8f1b8ebefda468a1270fa68ad2468b5de8804c7ab67"},"schema_version":"1.0","source":{"id":"2205.11790","kind":"arxiv","version":1}},"canonical_sha256":"a3f3b3ee81cd7a618da154747902fe930e2021b4fc0e0866c306d82acf33b33a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3f3b3ee81cd7a618da154747902fe930e2021b4fc0e0866c306d82acf33b33a","first_computed_at":"2026-07-05T04:26:08.371674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:08.371674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SdDpVSZ57KqobGokXjgUfgTkHsq2usS2eshPUrXyQLXLYPJWqbFIbvlg4xzm1qlbIRDJohh4ZK511/lsLRwyCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:08.372109Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fa4dcdcd6cd3580055d5695f74de27236311d00481fc2216caaf78bd6ec1e9d","sha256:d95f1708541401283768979afde81107bfa08f500ac62b2cfc92f444d5c4f5dd"],"state_sha256":"23df0ee0d0f35454f685aeb114fcaab85893617f60849ce5e960da929b06d4fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I5ZrvU188mpym+WhEjp2u3xs1rbtIlidr0LlkIRM7FZ9M/wiBH0dtsoNE/Q5wua73pjQya/rYSpjQnqHsCVlBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:07:45.121785Z","bundle_sha256":"3432c61994ad822e9e0492931a09c9d97c4f1ac81a746f2046f92a4e2076028f"}}