{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CLHRNOYTV27BS2PKYVPUUSQDMT","short_pith_number":"pith:CLHRNOYT","schema_version":"1.0","canonical_sha256":"12cf16bb13aebe1969eac55f4a4a0364f7a13098797f14486c9511de93e4a90f","source":{"kind":"arxiv","id":"1907.02057","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Model-Based Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Langlois, Guodong Zhang, Ignasi Clavera, Jerrick Hoang, Jimmy Ba, Pieter Abbeel, Shunshi Zhang, Tingwu Wang, Xuchan Bao, Yeming Wen","submitted_at":"2019-07-03T17:53:02Z","abstract_excerpt":"Model-based reinforcement learning (MBRL) is widely seen as having the potential to be significantly more sample efficient than model-free RL. However, research in model-based RL has not been very standardized. It is fairly common for authors to experiment with self-designed environments, and there are several separate lines of research, which are sometimes closed-sourced or not reproducible. Accordingly, it is an open question how these various existing MBRL algorithms perform relative to each other. To facilitate research in MBRL, in this paper we gather a wide collection of MBRL algorithms "},"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":"1907.02057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T17:53:02Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"b62637b9f1ecab98fb0d628203458e3edf9298c6966be2f552ce349f12497736","abstract_canon_sha256":"ba48bfa60fcebe020aa6b07edf616393cd959cc1c59e0b60c1216a5857467268"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:31.724562Z","signature_b64":"9KzraQF8tUprwLB0OhtpCdE0ySwAdzpq9jzrZqQ8zP/o2rmTujpGTVB5WgCAnc9M7zhhN3aL9jHkv+HovCDzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12cf16bb13aebe1969eac55f4a4a0364f7a13098797f14486c9511de93e4a90f","last_reissued_at":"2026-05-17T23:41:31.723871Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:31.723871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Model-Based Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Langlois, Guodong Zhang, Ignasi Clavera, Jerrick Hoang, Jimmy Ba, Pieter Abbeel, Shunshi Zhang, Tingwu Wang, Xuchan Bao, Yeming Wen","submitted_at":"2019-07-03T17:53:02Z","abstract_excerpt":"Model-based reinforcement learning (MBRL) is widely seen as having the potential to be significantly more sample efficient than model-free RL. However, research in model-based RL has not been very standardized. It is fairly common for authors to experiment with self-designed environments, and there are several separate lines of research, which are sometimes closed-sourced or not reproducible. Accordingly, it is an open question how these various existing MBRL algorithms perform relative to each other. To facilitate research in MBRL, in this paper we gather a wide collection of MBRL algorithms "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02057","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":""},"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":"1907.02057","created_at":"2026-05-17T23:41:31.723972+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.02057v1","created_at":"2026-05-17T23:41:31.723972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02057","created_at":"2026-05-17T23:41:31.723972+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLHRNOYTV27B","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLHRNOYTV27BS2PK","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLHRNOYT","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2510.03508","citing_title":"D2 Actor Critic: Diffusion Actor Meets Distributional Critic","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2211.15657","citing_title":"Is Conditional Generative Modeling all you need for Decision-Making?","ref_index":123,"is_internal_anchor":true},{"citing_arxiv_id":"2010.02193","citing_title":"Mastering Atari with Discrete World Models","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2108.03298","citing_title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"1912.01603","citing_title":"Dream to Control: Learning Behaviors by Latent Imagination","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01242","citing_title":"Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09035","citing_title":"Advantage-Guided Diffusion for Model-Based Reinforcement Learning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":202,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLHRNOYTV27BS2PKYVPUUSQDMT","json":"https://pith.science/pith/CLHRNOYTV27BS2PKYVPUUSQDMT.json","graph_json":"https://pith.science/api/pith-number/CLHRNOYTV27BS2PKYVPUUSQDMT/graph.json","events_json":"https://pith.science/api/pith-number/CLHRNOYTV27BS2PKYVPUUSQDMT/events.json","paper":"https://pith.science/paper/CLHRNOYT"},"agent_actions":{"view_html":"https://pith.science/pith/CLHRNOYTV27BS2PKYVPUUSQDMT","download_json":"https://pith.science/pith/CLHRNOYTV27BS2PKYVPUUSQDMT.json","view_paper":"https://pith.science/paper/CLHRNOYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.02057&json=true","fetch_graph":"https://pith.science/api/pith-number/CLHRNOYTV27BS2PKYVPUUSQDMT/graph.json","fetch_events":"https://pith.science/api/pith-number/CLHRNOYTV27BS2PKYVPUUSQDMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLHRNOYTV27BS2PKYVPUUSQDMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLHRNOYTV27BS2PKYVPUUSQDMT/action/storage_attestation","attest_author":"https://pith.science/pith/CLHRNOYTV27BS2PKYVPUUSQDMT/action/author_attestation","sign_citation":"https://pith.science/pith/CLHRNOYTV27BS2PKYVPUUSQDMT/action/citation_signature","submit_replication":"https://pith.science/pith/CLHRNOYTV27BS2PKYVPUUSQDMT/action/replication_record"}},"created_at":"2026-05-17T23:41:31.723972+00:00","updated_at":"2026-05-17T23:41:31.723972+00:00"}