{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VN7RHWLUFUZWPLJEKRQ23HBHOP","short_pith_number":"pith:VN7RHWLU","canonical_record":{"source":{"id":"2111.08550","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T15:24:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bad3f2646b7c79e494545143cf56a67bb29682b72b3ee30291697b1f121b454a","abstract_canon_sha256":"f2c0f2cec68b7bed31ec2e5c3087c1eeba414e4b8bbb52c516ab6c53db0a2be9"},"schema_version":"1.0"},"canonical_sha256":"ab7f13d9742d3367ad245461ad9c2773f36d1b80e9325762122fe356f59f59d5","source":{"kind":"arxiv","id":"2111.08550","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.08550","created_at":"2026-07-05T04:37:29Z"},{"alias_kind":"arxiv_version","alias_value":"2111.08550v3","created_at":"2026-07-05T04:37:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08550","created_at":"2026-07-05T04:37:29Z"},{"alias_kind":"pith_short_12","alias_value":"VN7RHWLUFUZW","created_at":"2026-07-05T04:37:29Z"},{"alias_kind":"pith_short_16","alias_value":"VN7RHWLUFUZWPLJE","created_at":"2026-07-05T04:37:29Z"},{"alias_kind":"pith_short_8","alias_value":"VN7RHWLU","created_at":"2026-07-05T04:37:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VN7RHWLUFUZWPLJEKRQ23HBHOP","target":"record","payload":{"canonical_record":{"source":{"id":"2111.08550","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T15:24:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bad3f2646b7c79e494545143cf56a67bb29682b72b3ee30291697b1f121b454a","abstract_canon_sha256":"f2c0f2cec68b7bed31ec2e5c3087c1eeba414e4b8bbb52c516ab6c53db0a2be9"},"schema_version":"1.0"},"canonical_sha256":"ab7f13d9742d3367ad245461ad9c2773f36d1b80e9325762122fe356f59f59d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:29.466396Z","signature_b64":"UwLv147Z/OGZm7Cg0dt53pPPHrszAwpjXPeoTk0cgH7NNLJ+S3HX8c+oC5NVssMGgO/LL8G+sg2Va4exrFOsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab7f13d9742d3367ad245461ad9c2773f36d1b80e9325762122fe356f59f59d5","last_reissued_at":"2026-07-05T04:37:29.465862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:29.465862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.08550","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":"2026-07-05T04:37:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ivBz9njFSvDpP2ExqlJU65H4eroWFZJkLjOYvixfMb2KZZ/+jW/3LsdaR+AOyPOZ1AIenXNieYaR2SYN/2tmCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:16:58.492010Z"},"content_sha256":"654c90e0f1d024165e7bb001988cd5cd9e460d55374fade3711ef2a09ba8feaf","schema_version":"1.0","event_id":"sha256:654c90e0f1d024165e7bb001988cd5cd9e460d55374fade3711ef2a09ba8feaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VN7RHWLUFUZWPLJEKRQ23HBHOP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Effective Scheduling of Model-based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hang Lai, Jian Shen, Ruiming Tang, Weinan Zhang, Xing Zhang, Yimin Huang, Yong Yu, Zhenguo Li","submitted_at":"2021-11-16T15:24:59Z","abstract_excerpt":"Model-based reinforcement learning has attracted wide attention due to its superior sample efficiency. Despite its impressive success so far, it is still unclear how to appropriately schedule the important hyperparameters to achieve adequate performance, such as the real data ratio for policy optimization in Dyna-style model-based algorithms. In this paper, we first theoretically analyze the role of real data in policy training, which suggests that gradually increasing the ratio of real data yields better performance. Inspired by the analysis, we propose a framework named AutoMBPO to automatic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08550","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/2111.08550/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":"2026-07-05T04:37:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W0+HcWpB6y6tz4Lw+mU2OYcnE1IPwIxGk7lO84+Vz1ANywgmbpv124+vtEmJmZD6l2TMAjivL5k/tcNCQp3BDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:16:58.492543Z"},"content_sha256":"1d121a604c3e2166e56a5ec47366a0b8dc3472e5fd681e2ec983b2c7c40fbddd","schema_version":"1.0","event_id":"sha256:1d121a604c3e2166e56a5ec47366a0b8dc3472e5fd681e2ec983b2c7c40fbddd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VN7RHWLUFUZWPLJEKRQ23HBHOP/bundle.json","state_url":"https://pith.science/pith/VN7RHWLUFUZWPLJEKRQ23HBHOP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VN7RHWLUFUZWPLJEKRQ23HBHOP/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":"2026-08-18T23:16:58Z","links":{"resolver":"https://pith.science/pith/VN7RHWLUFUZWPLJEKRQ23HBHOP","bundle":"https://pith.science/pith/VN7RHWLUFUZWPLJEKRQ23HBHOP/bundle.json","state":"https://pith.science/pith/VN7RHWLUFUZWPLJEKRQ23HBHOP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VN7RHWLUFUZWPLJEKRQ23HBHOP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VN7RHWLUFUZWPLJEKRQ23HBHOP","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":"f2c0f2cec68b7bed31ec2e5c3087c1eeba414e4b8bbb52c516ab6c53db0a2be9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T15:24:59Z","title_canon_sha256":"bad3f2646b7c79e494545143cf56a67bb29682b72b3ee30291697b1f121b454a"},"schema_version":"1.0","source":{"id":"2111.08550","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.08550","created_at":"2026-07-05T04:37:29Z"},{"alias_kind":"arxiv_version","alias_value":"2111.08550v3","created_at":"2026-07-05T04:37:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08550","created_at":"2026-07-05T04:37:29Z"},{"alias_kind":"pith_short_12","alias_value":"VN7RHWLUFUZW","created_at":"2026-07-05T04:37:29Z"},{"alias_kind":"pith_short_16","alias_value":"VN7RHWLUFUZWPLJE","created_at":"2026-07-05T04:37:29Z"},{"alias_kind":"pith_short_8","alias_value":"VN7RHWLU","created_at":"2026-07-05T04:37:29Z"}],"graph_snapshots":[{"event_id":"sha256:1d121a604c3e2166e56a5ec47366a0b8dc3472e5fd681e2ec983b2c7c40fbddd","target":"graph","created_at":"2026-07-05T04:37:29Z","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/2111.08550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning has attracted wide attention due to its superior sample efficiency. Despite its impressive success so far, it is still unclear how to appropriately schedule the important hyperparameters to achieve adequate performance, such as the real data ratio for policy optimization in Dyna-style model-based algorithms. In this paper, we first theoretically analyze the role of real data in policy training, which suggests that gradually increasing the ratio of real data yields better performance. Inspired by the analysis, we propose a framework named AutoMBPO to automatic","authors_text":"Hang Lai, Jian Shen, Ruiming Tang, Weinan Zhang, Xing Zhang, Yimin Huang, Yong Yu, Zhenguo Li","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T15:24:59Z","title":"On Effective Scheduling of Model-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08550","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":"sha256:654c90e0f1d024165e7bb001988cd5cd9e460d55374fade3711ef2a09ba8feaf","target":"record","created_at":"2026-07-05T04:37:29Z","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":"f2c0f2cec68b7bed31ec2e5c3087c1eeba414e4b8bbb52c516ab6c53db0a2be9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T15:24:59Z","title_canon_sha256":"bad3f2646b7c79e494545143cf56a67bb29682b72b3ee30291697b1f121b454a"},"schema_version":"1.0","source":{"id":"2111.08550","kind":"arxiv","version":3}},"canonical_sha256":"ab7f13d9742d3367ad245461ad9c2773f36d1b80e9325762122fe356f59f59d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab7f13d9742d3367ad245461ad9c2773f36d1b80e9325762122fe356f59f59d5","first_computed_at":"2026-07-05T04:37:29.465862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:37:29.465862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UwLv147Z/OGZm7Cg0dt53pPPHrszAwpjXPeoTk0cgH7NNLJ+S3HX8c+oC5NVssMGgO/LL8G+sg2Va4exrFOsAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:37:29.466396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.08550","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:654c90e0f1d024165e7bb001988cd5cd9e460d55374fade3711ef2a09ba8feaf","sha256:1d121a604c3e2166e56a5ec47366a0b8dc3472e5fd681e2ec983b2c7c40fbddd"],"state_sha256":"0f62e2806d0e410fad33e1e7adb993796622b6493d237f374417daa894a2e6d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKEpbzLlcVT3TvZ6M+YLEZsDEe08wd7UDkyOvuK5qH2COszMeq/ZoMQpcB/YltDgi1SgDjeAzCgeiNW47HLXBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:16:58.496461Z","bundle_sha256":"55fb65a84c24c4d26f7e5677307506f8c97b449d920b5a5f2f95d28d9e98fcf8"}}