{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:W667M6DUFNEIMR6HSJSLC2XSVH","short_pith_number":"pith:W667M6DU","canonical_record":{"source":{"id":"2206.09328","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-19T05:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"ce2b9314ae7d55e51458cf2b91be97f87c90c2e893b639079ee96a318ae9954d","abstract_canon_sha256":"48ae9e8f05dea4207a1ecda7ff6da2bf28aef6f6b86b4bbe2c737e8573860383"},"schema_version":"1.0"},"canonical_sha256":"b7bdf678742b488647c79264b16af2a9d82c32f27a7abb631f5308d75cd911a6","source":{"kind":"arxiv","id":"2206.09328","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.09328","created_at":"2026-07-05T04:33:06Z"},{"alias_kind":"arxiv_version","alias_value":"2206.09328v1","created_at":"2026-07-05T04:33:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09328","created_at":"2026-07-05T04:33:06Z"},{"alias_kind":"pith_short_12","alias_value":"W667M6DUFNEI","created_at":"2026-07-05T04:33:06Z"},{"alias_kind":"pith_short_16","alias_value":"W667M6DUFNEIMR6H","created_at":"2026-07-05T04:33:06Z"},{"alias_kind":"pith_short_8","alias_value":"W667M6DU","created_at":"2026-07-05T04:33:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:W667M6DUFNEIMR6HSJSLC2XSVH","target":"record","payload":{"canonical_record":{"source":{"id":"2206.09328","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-19T05:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"ce2b9314ae7d55e51458cf2b91be97f87c90c2e893b639079ee96a318ae9954d","abstract_canon_sha256":"48ae9e8f05dea4207a1ecda7ff6da2bf28aef6f6b86b4bbe2c737e8573860383"},"schema_version":"1.0"},"canonical_sha256":"b7bdf678742b488647c79264b16af2a9d82c32f27a7abb631f5308d75cd911a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:06.327507Z","signature_b64":"xQvrOPtXYuawEeK8AxzRkGctmFjTBuc3bSW9eNYTXZr7d7KsgR5ma1wRZl6+30m0Hs/te9oU6k6N7zgamsalCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7bdf678742b488647c79264b16af2a9d82c32f27a7abb631f5308d75cd911a6","last_reissued_at":"2026-07-05T04:33:06.327022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:06.327022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.09328","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:33:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9XqBeJlH4YL6iJWe8YOcDktbr8g242k6vtwIDmMJ2T7Q/Xljaqf6TBufnyuOHni6DDCXDzNd+OWQI0dLPTqJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:23:07.674398Z"},"content_sha256":"b063daedf2b4056cf6949062276110e5baf13455ed4be0ff369979ead7a9a9a2","schema_version":"1.0","event_id":"sha256:b063daedf2b4056cf6949062276110e5baf13455ed4be0ff369979ead7a9a9a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:W667M6DUFNEIMR6HSJSLC2XSVH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Model-based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fan-Ming Luo, Hang Lai, Tian Xu, Weinan Zhang, Xiong-Hui Chen, Yang Yu","submitted_at":"2022-06-19T05:28:03Z","abstract_excerpt":"Reinforcement learning (RL) solves sequential decision-making problems via a trial-and-error process interacting with the environment. While RL achieves outstanding success in playing complex video games that allow huge trial-and-error, making errors is always undesired in the real world. To improve the sample efficiency and thus reduce the errors, model-based reinforcement learning (MBRL) is believed to be a promising direction, which builds environment models in which the trial-and-errors can take place without real costs. In this survey, we take a review of MBRL with a focus on the recent p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09328","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/2206.09328/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":"2026-07-05T04:33:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U5glUN9mE2i+GLEXtK0/Xfa55CgEV8tcFSi56XZpnqc1cW21HEkP2040R9acmD1I91b7AvHl8xBPxdcw+YqnBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:23:07.674892Z"},"content_sha256":"0b213deba0adadf1b9074775a12a7a86c27fdb58354b03b1a2fd2b25fc2fbc0c","schema_version":"1.0","event_id":"sha256:0b213deba0adadf1b9074775a12a7a86c27fdb58354b03b1a2fd2b25fc2fbc0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W667M6DUFNEIMR6HSJSLC2XSVH/bundle.json","state_url":"https://pith.science/pith/W667M6DUFNEIMR6HSJSLC2XSVH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W667M6DUFNEIMR6HSJSLC2XSVH/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":"2026-08-08T07:23:07Z","links":{"resolver":"https://pith.science/pith/W667M6DUFNEIMR6HSJSLC2XSVH","bundle":"https://pith.science/pith/W667M6DUFNEIMR6HSJSLC2XSVH/bundle.json","state":"https://pith.science/pith/W667M6DUFNEIMR6HSJSLC2XSVH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W667M6DUFNEIMR6HSJSLC2XSVH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:W667M6DUFNEIMR6HSJSLC2XSVH","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":"48ae9e8f05dea4207a1ecda7ff6da2bf28aef6f6b86b4bbe2c737e8573860383","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-19T05:28:03Z","title_canon_sha256":"ce2b9314ae7d55e51458cf2b91be97f87c90c2e893b639079ee96a318ae9954d"},"schema_version":"1.0","source":{"id":"2206.09328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.09328","created_at":"2026-07-05T04:33:06Z"},{"alias_kind":"arxiv_version","alias_value":"2206.09328v1","created_at":"2026-07-05T04:33:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09328","created_at":"2026-07-05T04:33:06Z"},{"alias_kind":"pith_short_12","alias_value":"W667M6DUFNEI","created_at":"2026-07-05T04:33:06Z"},{"alias_kind":"pith_short_16","alias_value":"W667M6DUFNEIMR6H","created_at":"2026-07-05T04:33:06Z"},{"alias_kind":"pith_short_8","alias_value":"W667M6DU","created_at":"2026-07-05T04:33:06Z"}],"graph_snapshots":[{"event_id":"sha256:0b213deba0adadf1b9074775a12a7a86c27fdb58354b03b1a2fd2b25fc2fbc0c","target":"graph","created_at":"2026-07-05T04:33:06Z","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/2206.09328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) solves sequential decision-making problems via a trial-and-error process interacting with the environment. While RL achieves outstanding success in playing complex video games that allow huge trial-and-error, making errors is always undesired in the real world. To improve the sample efficiency and thus reduce the errors, model-based reinforcement learning (MBRL) is believed to be a promising direction, which builds environment models in which the trial-and-errors can take place without real costs. In this survey, we take a review of MBRL with a focus on the recent p","authors_text":"Fan-Ming Luo, Hang Lai, Tian Xu, Weinan Zhang, Xiong-Hui Chen, Yang Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-19T05:28:03Z","title":"A Survey on Model-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09328","kind":"arxiv","version":1},"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:b063daedf2b4056cf6949062276110e5baf13455ed4be0ff369979ead7a9a9a2","target":"record","created_at":"2026-07-05T04:33:06Z","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":"48ae9e8f05dea4207a1ecda7ff6da2bf28aef6f6b86b4bbe2c737e8573860383","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-19T05:28:03Z","title_canon_sha256":"ce2b9314ae7d55e51458cf2b91be97f87c90c2e893b639079ee96a318ae9954d"},"schema_version":"1.0","source":{"id":"2206.09328","kind":"arxiv","version":1}},"canonical_sha256":"b7bdf678742b488647c79264b16af2a9d82c32f27a7abb631f5308d75cd911a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7bdf678742b488647c79264b16af2a9d82c32f27a7abb631f5308d75cd911a6","first_computed_at":"2026-07-05T04:33:06.327022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:06.327022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xQvrOPtXYuawEeK8AxzRkGctmFjTBuc3bSW9eNYTXZr7d7KsgR5ma1wRZl6+30m0Hs/te9oU6k6N7zgamsalCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:06.327507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.09328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b063daedf2b4056cf6949062276110e5baf13455ed4be0ff369979ead7a9a9a2","sha256:0b213deba0adadf1b9074775a12a7a86c27fdb58354b03b1a2fd2b25fc2fbc0c"],"state_sha256":"525d74ae6de2063beb287643ba32a0b06bd4c0ec84d8c5785528a9a7ca7d515a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o1UD59BPWKITPWwDc8OIN0/Sj84AqRAGm189wWS7d0IuOWr8tMTLXv5Dd4QiifXV6Vwz6v7uP27RaVp6xgeeDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:23:07.679580Z","bundle_sha256":"15c154621a936591e4bc9273433d1a40a9a13f152b4332a61b7796d16c9db6f6"}}