{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UOUHGQI3V76NPAKSW47O5CBVAF","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":"afe6dd148384a14ddcb8152d0bf70312c3891bde244c89777ff72e8c506c65a8","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-12T20:06:52Z","title_canon_sha256":"32b1684d8b5d854323955ea3a09e2f1165aca776c8e8028fa5117f2be578281d"},"schema_version":"1.0","source":{"id":"2008.05556","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.05556","created_at":"2026-07-05T02:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"2008.05556v3","created_at":"2026-07-05T02:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05556","created_at":"2026-07-05T02:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"UOUHGQI3V76N","created_at":"2026-07-05T02:23:58Z"},{"alias_kind":"pith_short_16","alias_value":"UOUHGQI3V76NPAKS","created_at":"2026-07-05T02:23:58Z"},{"alias_kind":"pith_short_8","alias_value":"UOUHGQI3","created_at":"2026-07-05T02:23:58Z"}],"graph_snapshots":[{"event_id":"sha256:702daa4fffb3807e81cb069c3714c6b181f7ad90f4239b596a12ce920619a496","target":"graph","created_at":"2026-07-05T02:23:58Z","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/2008.05556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline learning is a key part of making reinforcement learning (RL) useable in real systems. Offline RL looks at scenarios where there is data from a system's operation, but no direct access to the system when learning a policy. Recent work on training RL policies from offline data has shown results both with model-free policies learned directly from the data, or with planning on top of learnt models of the data. Model-free policies tend to be more performant, but are more opaque, harder to command externally, and less easy to integrate into larger systems. We propose an offline learner that ","authors_text":"Arthur Argenson, Gabriel Dulac-Arnold","cross_cats":["cs.AI","cs.RO","cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-12T20:06:52Z","title":"Model-Based Offline Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05556","kind":"arxiv","version":3},"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:ef61d5d88b939d4dd8218e3feb892cdd7482283a14398f509b7b0beebb00b862","target":"record","created_at":"2026-07-05T02:23:58Z","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":"afe6dd148384a14ddcb8152d0bf70312c3891bde244c89777ff72e8c506c65a8","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-12T20:06:52Z","title_canon_sha256":"32b1684d8b5d854323955ea3a09e2f1165aca776c8e8028fa5117f2be578281d"},"schema_version":"1.0","source":{"id":"2008.05556","kind":"arxiv","version":3}},"canonical_sha256":"a3a873411baffcd78152b73eee8835014174f3d11ef4b0b9ee49630c2c4eeae3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3a873411baffcd78152b73eee8835014174f3d11ef4b0b9ee49630c2c4eeae3","first_computed_at":"2026-07-05T02:23:58.064286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:23:58.064286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+KjGtLbkXpTLOfrTz3cknoWNPWu95BQvpYatoGvBDxOgVmBBUrDiaiQ8FGXdblRpzGwCfZHpLS67/lCoN4n9CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:23:58.064783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.05556","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef61d5d88b939d4dd8218e3feb892cdd7482283a14398f509b7b0beebb00b862","sha256:702daa4fffb3807e81cb069c3714c6b181f7ad90f4239b596a12ce920619a496"],"state_sha256":"7736b538d4b8b3835facbeb01a4d546948939277f17be87fa33eb6e16cfc19ca"}