{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:A5VLCEPGHGZASAOOM4DD3ADIWV","short_pith_number":"pith:A5VLCEPG","canonical_record":{"source":{"id":"2210.05922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T04:58:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e92862ca055c3763742f0618f2a4ecc90b28225c821f602aadd34c9717cc698f","abstract_canon_sha256":"331522e4c3f1b5d262478313cdcc68bb07ee23c35855b89ac08eefe28e260f7f"},"schema_version":"1.0"},"canonical_sha256":"076ab111e639b20901ce67063d8068b57258d177fd1c54ddc37ff69c6a7b15bc","source":{"kind":"arxiv","id":"2210.05922","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05922","created_at":"2026-07-05T05:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05922v1","created_at":"2026-07-05T05:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05922","created_at":"2026-07-05T05:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"A5VLCEPGHGZA","created_at":"2026-07-05T05:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"A5VLCEPGHGZASAOO","created_at":"2026-07-05T05:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"A5VLCEPG","created_at":"2026-07-05T05:05:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:A5VLCEPGHGZASAOOM4DD3ADIWV","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T04:58:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e92862ca055c3763742f0618f2a4ecc90b28225c821f602aadd34c9717cc698f","abstract_canon_sha256":"331522e4c3f1b5d262478313cdcc68bb07ee23c35855b89ac08eefe28e260f7f"},"schema_version":"1.0"},"canonical_sha256":"076ab111e639b20901ce67063d8068b57258d177fd1c54ddc37ff69c6a7b15bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:54.402044Z","signature_b64":"Abw9qWiGUmdCqy82WxNoamydauBPPbhxZhMuDGWBuCNnH4SI9AoTxtn6BtQmUsksRfaARjNYmNlVG9w41f1GBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"076ab111e639b20901ce67063d8068b57258d177fd1c54ddc37ff69c6a7b15bc","last_reissued_at":"2026-07-05T05:05:54.401611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:54.401611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05922","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":"2026-07-05T05:05:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b9znewvH+c6CMbfaKUwVFdJxla65xr1eFptAtysEIoBu15VcgiEO9f9aGq/Elyrx6+ZUbwMouqGR1KFIN4CNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:07:10.998593Z"},"content_sha256":"3fac160230967148adaa59d45a087cf2cbda90338c301e30644c423c2cd706d9","schema_version":"1.0","event_id":"sha256:3fac160230967148adaa59d45a087cf2cbda90338c301e30644c423c2cd706d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:A5VLCEPGHGZASAOOM4DD3ADIWV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Unified Framework for Alternating Offline Model Training and Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mingyuan Zhou, Shentao Yang, Shujian Zhang, Yihao Feng","submitted_at":"2022-10-12T04:58:51Z","abstract_excerpt":"In offline model-based reinforcement learning (offline MBRL), we learn a dynamic model from historically collected data, and subsequently utilize the learned model and fixed datasets for policy learning, without further interacting with the environment. Offline MBRL algorithms can improve the efficiency and stability of policy learning over the model-free algorithms. However, in most of the existing offline MBRL algorithms, the learning objectives for the dynamic models and the policies are isolated from each other. Such an objective mismatch may lead to inferior performance of the learned age"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05922","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/2210.05922/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":"2026-07-05T05:05:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zNu799AlgHSAcbmygz2cKgPT7Ok2X2/i8GSQWUGr0cOPvReoV3rgX+XYRzErSnXx+kk70LQOtIrGfOolBKJOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:07:10.999106Z"},"content_sha256":"85ae57832e6360ca3a84164d08cfece24190ddabd90b4d19fcb0f2b9679b8784","schema_version":"1.0","event_id":"sha256:85ae57832e6360ca3a84164d08cfece24190ddabd90b4d19fcb0f2b9679b8784"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5VLCEPGHGZASAOOM4DD3ADIWV/bundle.json","state_url":"https://pith.science/pith/A5VLCEPGHGZASAOOM4DD3ADIWV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5VLCEPGHGZASAOOM4DD3ADIWV/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":"2026-08-07T04:07:11Z","links":{"resolver":"https://pith.science/pith/A5VLCEPGHGZASAOOM4DD3ADIWV","bundle":"https://pith.science/pith/A5VLCEPGHGZASAOOM4DD3ADIWV/bundle.json","state":"https://pith.science/pith/A5VLCEPGHGZASAOOM4DD3ADIWV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5VLCEPGHGZASAOOM4DD3ADIWV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A5VLCEPGHGZASAOOM4DD3ADIWV","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":"331522e4c3f1b5d262478313cdcc68bb07ee23c35855b89ac08eefe28e260f7f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T04:58:51Z","title_canon_sha256":"e92862ca055c3763742f0618f2a4ecc90b28225c821f602aadd34c9717cc698f"},"schema_version":"1.0","source":{"id":"2210.05922","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05922","created_at":"2026-07-05T05:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05922v1","created_at":"2026-07-05T05:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05922","created_at":"2026-07-05T05:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"A5VLCEPGHGZA","created_at":"2026-07-05T05:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"A5VLCEPGHGZASAOO","created_at":"2026-07-05T05:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"A5VLCEPG","created_at":"2026-07-05T05:05:54Z"}],"graph_snapshots":[{"event_id":"sha256:85ae57832e6360ca3a84164d08cfece24190ddabd90b4d19fcb0f2b9679b8784","target":"graph","created_at":"2026-07-05T05:05:54Z","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/2210.05922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline model-based reinforcement learning (offline MBRL), we learn a dynamic model from historically collected data, and subsequently utilize the learned model and fixed datasets for policy learning, without further interacting with the environment. Offline MBRL algorithms can improve the efficiency and stability of policy learning over the model-free algorithms. However, in most of the existing offline MBRL algorithms, the learning objectives for the dynamic models and the policies are isolated from each other. Such an objective mismatch may lead to inferior performance of the learned age","authors_text":"Mingyuan Zhou, Shentao Yang, Shujian Zhang, Yihao Feng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T04:58:51Z","title":"A Unified Framework for Alternating Offline Model Training and Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05922","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":"sha256:3fac160230967148adaa59d45a087cf2cbda90338c301e30644c423c2cd706d9","target":"record","created_at":"2026-07-05T05:05:54Z","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":"331522e4c3f1b5d262478313cdcc68bb07ee23c35855b89ac08eefe28e260f7f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T04:58:51Z","title_canon_sha256":"e92862ca055c3763742f0618f2a4ecc90b28225c821f602aadd34c9717cc698f"},"schema_version":"1.0","source":{"id":"2210.05922","kind":"arxiv","version":1}},"canonical_sha256":"076ab111e639b20901ce67063d8068b57258d177fd1c54ddc37ff69c6a7b15bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"076ab111e639b20901ce67063d8068b57258d177fd1c54ddc37ff69c6a7b15bc","first_computed_at":"2026-07-05T05:05:54.401611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:54.401611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Abw9qWiGUmdCqy82WxNoamydauBPPbhxZhMuDGWBuCNnH4SI9AoTxtn6BtQmUsksRfaARjNYmNlVG9w41f1GBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:54.402044Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05922","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fac160230967148adaa59d45a087cf2cbda90338c301e30644c423c2cd706d9","sha256:85ae57832e6360ca3a84164d08cfece24190ddabd90b4d19fcb0f2b9679b8784"],"state_sha256":"27de730bdd26cb5cb061a63d2241ae155e08d1f58224113ad675da27276d82e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fhe8YTZ6GeYFvV5lJN7qzxdFH35pGGZq7VJUo0VSKeH2D1X5T9wyRsFUkO+7MDzeczfqGCGcDN3IY3gbp271Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:07:11.003459Z","bundle_sha256":"f8e911bdd5e82a8e80559490905bac56fe51d0ee3792f4d1f346cce700099ac4"}}