{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UOUHGQI3V76NPAKSW47O5CBVAF","short_pith_number":"pith:UOUHGQI3","schema_version":"1.0","canonical_sha256":"a3a873411baffcd78152b73eee8835014174f3d11ef4b0b9ee49630c2c4eeae3","source":{"kind":"arxiv","id":"2008.05556","version":3},"attestation_state":"computed","paper":{"title":"Model-Based Offline Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Argenson, Gabriel Dulac-Arnold","submitted_at":"2020-08-12T20:06:52Z","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 "},"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":"2008.05556","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-12T20:06:52Z","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"32b1684d8b5d854323955ea3a09e2f1165aca776c8e8028fa5117f2be578281d","abstract_canon_sha256":"afe6dd148384a14ddcb8152d0bf70312c3891bde244c89777ff72e8c506c65a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:23:58.064783Z","signature_b64":"+KjGtLbkXpTLOfrTz3cknoWNPWu95BQvpYatoGvBDxOgVmBBUrDiaiQ8FGXdblRpzGwCfZHpLS67/lCoN4n9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3a873411baffcd78152b73eee8835014174f3d11ef4b0b9ee49630c2c4eeae3","last_reissued_at":"2026-07-05T02:23:58.064286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:23:58.064286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Based Offline Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Argenson, Gabriel Dulac-Arnold","submitted_at":"2020-08-12T20:06:52Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05556","kind":"arxiv","version":3},"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/2008.05556/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":"2008.05556","created_at":"2026-07-05T02:23:58.064353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.05556v3","created_at":"2026-07-05T02:23:58.064353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05556","created_at":"2026-07-05T02:23:58.064353+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOUHGQI3V76N","created_at":"2026-07-05T02:23:58.064353+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOUHGQI3V76NPAKS","created_at":"2026-07-05T02:23:58.064353+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOUHGQI3","created_at":"2026-07-05T02:23:58.064353+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2211.15657","citing_title":"Is Conditional Generative Modeling all you need for Decision-Making?","ref_index":258,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04528","citing_title":"Receding-Horizon Control via Drifting Models","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UOUHGQI3V76NPAKSW47O5CBVAF","json":"https://pith.science/pith/UOUHGQI3V76NPAKSW47O5CBVAF.json","graph_json":"https://pith.science/api/pith-number/UOUHGQI3V76NPAKSW47O5CBVAF/graph.json","events_json":"https://pith.science/api/pith-number/UOUHGQI3V76NPAKSW47O5CBVAF/events.json","paper":"https://pith.science/paper/UOUHGQI3"},"agent_actions":{"view_html":"https://pith.science/pith/UOUHGQI3V76NPAKSW47O5CBVAF","download_json":"https://pith.science/pith/UOUHGQI3V76NPAKSW47O5CBVAF.json","view_paper":"https://pith.science/paper/UOUHGQI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.05556&json=true","fetch_graph":"https://pith.science/api/pith-number/UOUHGQI3V76NPAKSW47O5CBVAF/graph.json","fetch_events":"https://pith.science/api/pith-number/UOUHGQI3V76NPAKSW47O5CBVAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOUHGQI3V76NPAKSW47O5CBVAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOUHGQI3V76NPAKSW47O5CBVAF/action/storage_attestation","attest_author":"https://pith.science/pith/UOUHGQI3V76NPAKSW47O5CBVAF/action/author_attestation","sign_citation":"https://pith.science/pith/UOUHGQI3V76NPAKSW47O5CBVAF/action/citation_signature","submit_replication":"https://pith.science/pith/UOUHGQI3V76NPAKSW47O5CBVAF/action/replication_record"}},"created_at":"2026-07-05T02:23:58.064353+00:00","updated_at":"2026-07-05T02:23:58.064353+00:00"}