{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5AMTYPH2UFPVIFHMSAZOBQMJU6","short_pith_number":"pith:5AMTYPH2","schema_version":"1.0","canonical_sha256":"e8193c3cfaa15f5414ec9032e0c189a7895aba9c169154c99d3bfb228c7189fc","source":{"kind":"arxiv","id":"2005.05951","version":3},"attestation_state":"computed","paper":{"title":"MOReL : Model-Based Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aravind Rajeswaran, Praneeth Netrapalli, Rahul Kidambi, Thorsten Joachims","submitted_at":"2020-05-12T17:52:43Z","abstract_excerpt":"In offline reinforcement learning (RL), the goal is to learn a highly rewarding policy based solely on a dataset of historical interactions with the environment. The ability to train RL policies offline can greatly expand the applicability of RL, its data efficiency, and its experimental velocity. Prior work in offline RL has been confined almost exclusively to model-free RL approaches. In this work, we present MOReL, an algorithmic framework for model-based offline RL. This framework consists of two steps: (a) learning a pessimistic MDP (P-MDP) using the offline dataset; and (b) learning a ne"},"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":"2005.05951","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-12T17:52:43Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cb5711d47e2616f39333aeb1a5e072c5b3f63a0689287a11ac25f00a14cceca7","abstract_canon_sha256":"4769915cae0aa63667030bddf5af6b1d9c0ce45c94895b0dc2aa568c937963ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:19:14.978677Z","signature_b64":"hic0PEzk16NFjiLLXaOKBck6pnF96ebrYGomnMl/e5LPuFxd/8pkCGWz8McWrKnCygM642gjYYBB+5PHSf2TDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8193c3cfaa15f5414ec9032e0c189a7895aba9c169154c99d3bfb228c7189fc","last_reissued_at":"2026-07-05T02:19:14.978169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:19:14.978169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOReL : Model-Based Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aravind Rajeswaran, Praneeth Netrapalli, Rahul Kidambi, Thorsten Joachims","submitted_at":"2020-05-12T17:52:43Z","abstract_excerpt":"In offline reinforcement learning (RL), the goal is to learn a highly rewarding policy based solely on a dataset of historical interactions with the environment. The ability to train RL policies offline can greatly expand the applicability of RL, its data efficiency, and its experimental velocity. Prior work in offline RL has been confined almost exclusively to model-free RL approaches. In this work, we present MOReL, an algorithmic framework for model-based offline RL. This framework consists of two steps: (a) learning a pessimistic MDP (P-MDP) using the offline dataset; and (b) learning a ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.05951","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/2005.05951/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":"2005.05951","created_at":"2026-07-05T02:19:14.978228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.05951v3","created_at":"2026-07-05T02:19:14.978228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05951","created_at":"2026-07-05T02:19:14.978228+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AMTYPH2UFPV","created_at":"2026-07-05T02:19:14.978228+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AMTYPH2UFPVIFHM","created_at":"2026-07-05T02:19:14.978228+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AMTYPH2","created_at":"2026-07-05T02:19:14.978228+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18610","citing_title":"SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19328","citing_title":"UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18610","citing_title":"SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01346","citing_title":"Safety, Security, and Cognitive Risks in World Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2108.03298","citing_title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2005.01643","citing_title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","ref_index":237,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6","json":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6.json","graph_json":"https://pith.science/api/pith-number/5AMTYPH2UFPVIFHMSAZOBQMJU6/graph.json","events_json":"https://pith.science/api/pith-number/5AMTYPH2UFPVIFHMSAZOBQMJU6/events.json","paper":"https://pith.science/paper/5AMTYPH2"},"agent_actions":{"view_html":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6","download_json":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6.json","view_paper":"https://pith.science/paper/5AMTYPH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.05951&json=true","fetch_graph":"https://pith.science/api/pith-number/5AMTYPH2UFPVIFHMSAZOBQMJU6/graph.json","fetch_events":"https://pith.science/api/pith-number/5AMTYPH2UFPVIFHMSAZOBQMJU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6/action/storage_attestation","attest_author":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6/action/author_attestation","sign_citation":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6/action/citation_signature","submit_replication":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6/action/replication_record"}},"created_at":"2026-07-05T02:19:14.978228+00:00","updated_at":"2026-07-05T02:19:14.978228+00:00"}