{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U5N5WIGL7KZCXRMB32QVV5SLVQ","short_pith_number":"pith:U5N5WIGL","schema_version":"1.0","canonical_sha256":"a75bdb20cbfab22bc581dea15af64bac0326e3b1580a8a682709ea252d6c048b","source":{"kind":"arxiv","id":"2104.10159","version":1},"attestation_state":"computed","paper":{"title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Amy Zhang, Brandon Amos, Luis Pineda, Nathan O. Lambert, Roberto Calandra","submitted_at":"2021-04-20T17:58:22Z","abstract_excerpt":"Model-based reinforcement learning is a compelling framework for data-efficient learning of agents that interact with the world. This family of algorithms has many subcomponents that need to be carefully selected and tuned. As a result the entry-bar for researchers to approach the field and to deploy it in real-world tasks can be daunting. In this paper, we present MBRL-Lib -- a machine learning library for model-based reinforcement learning in continuous state-action spaces based on PyTorch. MBRL-Lib is designed as a platform for both researchers, to easily develop, debug and compare new algo"},"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":"2104.10159","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-04-20T17:58:22Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"2ac17fad60defdbba75935ba98159b329aa6e7f9eae436f93c82dc1ec1128667","abstract_canon_sha256":"34f9c152294f9316ee5833e0b4dfd0d3ad7f3f21fea3caba777331d016ecc5a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:40.498807Z","signature_b64":"0sY3hqd+jGdUS7bRoIKKBeZTUc2ZKfaVz59PNCDrr46LNMb8TTQciVtMYfV89WMi23sNwIPRAN5CemsxtQ/gDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a75bdb20cbfab22bc581dea15af64bac0326e3b1580a8a682709ea252d6c048b","last_reissued_at":"2026-07-05T02:33:40.498247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:40.498247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Amy Zhang, Brandon Amos, Luis Pineda, Nathan O. Lambert, Roberto Calandra","submitted_at":"2021-04-20T17:58:22Z","abstract_excerpt":"Model-based reinforcement learning is a compelling framework for data-efficient learning of agents that interact with the world. This family of algorithms has many subcomponents that need to be carefully selected and tuned. As a result the entry-bar for researchers to approach the field and to deploy it in real-world tasks can be daunting. In this paper, we present MBRL-Lib -- a machine learning library for model-based reinforcement learning in continuous state-action spaces based on PyTorch. MBRL-Lib is designed as a platform for both researchers, to easily develop, debug and compare new algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.10159","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/2104.10159/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":"2104.10159","created_at":"2026-07-05T02:33:40.498321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.10159v1","created_at":"2026-07-05T02:33:40.498321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.10159","created_at":"2026-07-05T02:33:40.498321+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5N5WIGL7KZC","created_at":"2026-07-05T02:33:40.498321+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5N5WIGL7KZCXRMB","created_at":"2026-07-05T02:33:40.498321+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5N5WIGL","created_at":"2026-07-05T02:33:40.498321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24991","citing_title":"Solving Markov Decision Processes with Future Information via MPC","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31291","citing_title":"Deep Reinforcement Learning for Spacecraft Attitude Control During Atmospheric Re-Entry","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21800","citing_title":"stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06463","citing_title":"A Control Barrier Function-Constrained Model Predictive Control Framework for Safe Reinforcement Learning","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5N5WIGL7KZCXRMB32QVV5SLVQ","json":"https://pith.science/pith/U5N5WIGL7KZCXRMB32QVV5SLVQ.json","graph_json":"https://pith.science/api/pith-number/U5N5WIGL7KZCXRMB32QVV5SLVQ/graph.json","events_json":"https://pith.science/api/pith-number/U5N5WIGL7KZCXRMB32QVV5SLVQ/events.json","paper":"https://pith.science/paper/U5N5WIGL"},"agent_actions":{"view_html":"https://pith.science/pith/U5N5WIGL7KZCXRMB32QVV5SLVQ","download_json":"https://pith.science/pith/U5N5WIGL7KZCXRMB32QVV5SLVQ.json","view_paper":"https://pith.science/paper/U5N5WIGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.10159&json=true","fetch_graph":"https://pith.science/api/pith-number/U5N5WIGL7KZCXRMB32QVV5SLVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/U5N5WIGL7KZCXRMB32QVV5SLVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5N5WIGL7KZCXRMB32QVV5SLVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5N5WIGL7KZCXRMB32QVV5SLVQ/action/storage_attestation","attest_author":"https://pith.science/pith/U5N5WIGL7KZCXRMB32QVV5SLVQ/action/author_attestation","sign_citation":"https://pith.science/pith/U5N5WIGL7KZCXRMB32QVV5SLVQ/action/citation_signature","submit_replication":"https://pith.science/pith/U5N5WIGL7KZCXRMB32QVV5SLVQ/action/replication_record"}},"created_at":"2026-07-05T02:33:40.498321+00:00","updated_at":"2026-07-05T02:33:40.498321+00:00"}