{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RNQI7ULB3IOJ7F6YL2ZZDWUULY","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":"f1690dad38ce20249c59afe1692fd04628d8bfb755c7beb6a27f174904b92224","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T03:08:40Z","title_canon_sha256":"65db5b8938914f7df2e1fc34e8c7d619ee168c732629082cac16525bcc26b6fc"},"schema_version":"1.0","source":{"id":"1805.09496","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09496","created_at":"2026-05-17T23:44:10Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09496v6","created_at":"2026-05-17T23:44:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09496","created_at":"2026-05-17T23:44:10Z"},{"alias_kind":"pith_short_12","alias_value":"RNQI7ULB3IOJ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RNQI7ULB3IOJ7F6Y","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RNQI7ULB","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:1cfabf8d0828914d9880fd2d3301f1fd650562d4f9c8507b147fa40ef1888f4d","target":"graph","created_at":"2026-05-17T23:44:10Z","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"},"paper":{"abstract_excerpt":"Model-based reinforcement learning (MBRL) has been proposed as a promising alternative solution to tackle the high sampling cost challenge in the canonical reinforcement learning (RL), by leveraging a learned model to generate synthesized data for policy training purpose. The MBRL framework, nevertheless, is inherently limited by the convoluted process of jointly learning control policy and configuring hyper-parameters (e.g., global/local models, real and synthesized data, etc). The training process could be tedious and prohibitively costly. In this research, we propose an \"reinforcement on re","authors_text":"Kyle Guan, Linsen Dong, Xin Zhou, Yonggang Wen, Yuanlong Li","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T03:08:40Z","title":"Intelligent Trainer for Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09496","kind":"arxiv","version":6},"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":"sha256:688048180b23d1279300d0d90b3fc594c3f4fda19aabc8402ce5956f6b1256b7","target":"record","created_at":"2026-05-17T23:44:10Z","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":"f1690dad38ce20249c59afe1692fd04628d8bfb755c7beb6a27f174904b92224","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T03:08:40Z","title_canon_sha256":"65db5b8938914f7df2e1fc34e8c7d619ee168c732629082cac16525bcc26b6fc"},"schema_version":"1.0","source":{"id":"1805.09496","kind":"arxiv","version":6}},"canonical_sha256":"8b608fd161da1c9f97d85eb391da945e0314a7e6ae415dae10d2324914bcfcca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b608fd161da1c9f97d85eb391da945e0314a7e6ae415dae10d2324914bcfcca","first_computed_at":"2026-05-17T23:44:10.196537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:10.196537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8OsFEMkKUQoNrB6+7z7dXI6rOuYJ5bkZv30K6m9lxSvuAxNJbppw1JouCqV05OhIaSaxIxv0Ay+pDKtGdaJkBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:10.197081Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09496","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:688048180b23d1279300d0d90b3fc594c3f4fda19aabc8402ce5956f6b1256b7","sha256:1cfabf8d0828914d9880fd2d3301f1fd650562d4f9c8507b147fa40ef1888f4d"],"state_sha256":"b1eeaf910089ca4bacd36c4ffbdcbb89d9f52d662a5a00196ac16024345226ff"}