{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:5AMTYPH2UFPVIFHMSAZOBQMJU6","short_pith_number":"pith:5AMTYPH2","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"},"canonical_sha256":"e8193c3cfaa15f5414ec9032e0c189a7895aba9c169154c99d3bfb228c7189fc","source":{"kind":"arxiv","id":"2005.05951","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.05951","created_at":"2026-07-05T02:19:14Z"},{"alias_kind":"arxiv_version","alias_value":"2005.05951v3","created_at":"2026-07-05T02:19:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05951","created_at":"2026-07-05T02:19:14Z"},{"alias_kind":"pith_short_12","alias_value":"5AMTYPH2UFPV","created_at":"2026-07-05T02:19:14Z"},{"alias_kind":"pith_short_16","alias_value":"5AMTYPH2UFPVIFHM","created_at":"2026-07-05T02:19:14Z"},{"alias_kind":"pith_short_8","alias_value":"5AMTYPH2","created_at":"2026-07-05T02:19:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:5AMTYPH2UFPVIFHMSAZOBQMJU6","target":"record","payload":{"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"},"canonical_sha256":"e8193c3cfaa15f5414ec9032e0c189a7895aba9c169154c99d3bfb228c7189fc","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"},"source_kind":"arxiv","source_id":"2005.05951","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:19:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lOffgkL321GbLHHdFqeHX5HlrRn3Gw4QEd4+aMMGYUPjiCJTCtBgnZNy9LtLiPab+ROHG1UrPvKStVp3ZS9ICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:58:09.857243Z"},"content_sha256":"afef8e0f3487f3c237e86226bd5c61b5f52eeb74bdfb7f957f1d40625e3b111c","schema_version":"1.0","event_id":"sha256:afef8e0f3487f3c237e86226bd5c61b5f52eeb74bdfb7f957f1d40625e3b111c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:5AMTYPH2UFPVIFHMSAZOBQMJU6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:19:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"acwX3O6DvtZDpta8T9k3AV6mosVi5OLVu/t/jdkJVtUpix/z6GPJdmN/13nQ20XFmgjodd2o68vjaOOzS8UuAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:58:09.857751Z"},"content_sha256":"597dddac3c529a7bf9c2a2854c083ef46292b4b249b7bc582ef4d250cf530666","schema_version":"1.0","event_id":"sha256:597dddac3c529a7bf9c2a2854c083ef46292b4b249b7bc582ef4d250cf530666"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6/bundle.json","state_url":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6/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":"2026-08-06T09:58:09Z","links":{"resolver":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6","bundle":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6/bundle.json","state":"https://pith.science/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5AMTYPH2UFPVIFHMSAZOBQMJU6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5AMTYPH2UFPVIFHMSAZOBQMJU6","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":"4769915cae0aa63667030bddf5af6b1d9c0ce45c94895b0dc2aa568c937963ff","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-12T17:52:43Z","title_canon_sha256":"cb5711d47e2616f39333aeb1a5e072c5b3f63a0689287a11ac25f00a14cceca7"},"schema_version":"1.0","source":{"id":"2005.05951","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.05951","created_at":"2026-07-05T02:19:14Z"},{"alias_kind":"arxiv_version","alias_value":"2005.05951v3","created_at":"2026-07-05T02:19:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05951","created_at":"2026-07-05T02:19:14Z"},{"alias_kind":"pith_short_12","alias_value":"5AMTYPH2UFPV","created_at":"2026-07-05T02:19:14Z"},{"alias_kind":"pith_short_16","alias_value":"5AMTYPH2UFPVIFHM","created_at":"2026-07-05T02:19:14Z"},{"alias_kind":"pith_short_8","alias_value":"5AMTYPH2","created_at":"2026-07-05T02:19:14Z"}],"graph_snapshots":[{"event_id":"sha256:597dddac3c529a7bf9c2a2854c083ef46292b4b249b7bc582ef4d250cf530666","target":"graph","created_at":"2026-07-05T02:19:14Z","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/2005.05951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aravind Rajeswaran, Praneeth Netrapalli, Rahul Kidambi, Thorsten Joachims","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-12T17:52:43Z","title":"MOReL : Model-Based Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.05951","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:afef8e0f3487f3c237e86226bd5c61b5f52eeb74bdfb7f957f1d40625e3b111c","target":"record","created_at":"2026-07-05T02:19:14Z","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":"4769915cae0aa63667030bddf5af6b1d9c0ce45c94895b0dc2aa568c937963ff","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-12T17:52:43Z","title_canon_sha256":"cb5711d47e2616f39333aeb1a5e072c5b3f63a0689287a11ac25f00a14cceca7"},"schema_version":"1.0","source":{"id":"2005.05951","kind":"arxiv","version":3}},"canonical_sha256":"e8193c3cfaa15f5414ec9032e0c189a7895aba9c169154c99d3bfb228c7189fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8193c3cfaa15f5414ec9032e0c189a7895aba9c169154c99d3bfb228c7189fc","first_computed_at":"2026-07-05T02:19:14.978169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:19:14.978169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hic0PEzk16NFjiLLXaOKBck6pnF96ebrYGomnMl/e5LPuFxd/8pkCGWz8McWrKnCygM642gjYYBB+5PHSf2TDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:19:14.978677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.05951","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afef8e0f3487f3c237e86226bd5c61b5f52eeb74bdfb7f957f1d40625e3b111c","sha256:597dddac3c529a7bf9c2a2854c083ef46292b4b249b7bc582ef4d250cf530666"],"state_sha256":"98bae13028186f94c0de9f16449860216263c38f1a2f0214a527c0d45e0bd162"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"47u7+MyvcP/vpHW32TUKbgDKI+Mjgw8JkpWB9j+ceNV72lC+BzhQ2J0uTFvDM980yX9xw4AmIIVQM5bhSlJsCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:58:09.861092Z","bundle_sha256":"b668aafea6f79c44a90130bafc9f65438e2510cd72a157d841f77a459eff99f9"}}