{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BOBLKIUD2XK43S2CJVAOGPMTLU","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":"0777a2f0412ed8c27b743e42526f2b2f8676e71da7a71a303570fb2c9ef10a08","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-11T21:13:37Z","title_canon_sha256":"978e1b4bead0c31fdbaf8c5b37b83a869ea4ab64f0e2d7789da523bbb12d0750"},"schema_version":"1.0","source":{"id":"2005.05440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.05440","created_at":"2026-07-05T02:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2005.05440v1","created_at":"2026-07-05T02:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05440","created_at":"2026-07-05T02:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"BOBLKIUD2XK4","created_at":"2026-07-05T02:38:13Z"},{"alias_kind":"pith_short_16","alias_value":"BOBLKIUD2XK43S2C","created_at":"2026-07-05T02:38:13Z"},{"alias_kind":"pith_short_8","alias_value":"BOBLKIUD","created_at":"2026-07-05T02:38:13Z"}],"graph_snapshots":[{"event_id":"sha256:674a344ebebc8874f50968783d5952893235dde696d4cf59604631189e759fcb","target":"graph","created_at":"2026-07-05T02:38:13Z","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/2005.05440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Action delays degrade the performance of reinforcement learning in many real-world systems. This paper proposes a formal definition of delay-aware Markov Decision Process and proves it can be transformed into standard MDP with augmented states using the Markov reward process. We develop a delay-aware model-based reinforcement learning framework that can incorporate the multi-step delay into the learned system models without learning effort. Experiments with the Gym and MuJoCo platforms show that the proposed delay-aware model-based algorithm is more efficient in training and transferable betwe","authors_text":"Baiming Chen, Ding Zhao, Liang Li, Mengdi Xu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-11T21:13:37Z","title":"Delay-Aware Model-Based Reinforcement Learning for Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.05440","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":"sha256:0f36538cdcea05308a5c2dd13316d24a79ee1b7e80c582acb1239973c9d7a18f","target":"record","created_at":"2026-07-05T02:38:13Z","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":"0777a2f0412ed8c27b743e42526f2b2f8676e71da7a71a303570fb2c9ef10a08","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-11T21:13:37Z","title_canon_sha256":"978e1b4bead0c31fdbaf8c5b37b83a869ea4ab64f0e2d7789da523bbb12d0750"},"schema_version":"1.0","source":{"id":"2005.05440","kind":"arxiv","version":1}},"canonical_sha256":"0b82b52283d5d5cdcb424d40e33d935d33da81224894cbced9d9e0d8912e899d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b82b52283d5d5cdcb424d40e33d935d33da81224894cbced9d9e0d8912e899d","first_computed_at":"2026-07-05T02:38:13.917835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:38:13.917835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8I7LorW9GPxDfz6fing41wd70I4fqkLedShQSDTPtp+X6WzCnXTmqAQHSdeKkUyjgvIUnscfxQEwtyCw41hiAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:38:13.918264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.05440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f36538cdcea05308a5c2dd13316d24a79ee1b7e80c582acb1239973c9d7a18f","sha256:674a344ebebc8874f50968783d5952893235dde696d4cf59604631189e759fcb"],"state_sha256":"58248445bdd2f78cfbca54bd2f5b1bb573276081d02bd0650653dc41ab0107e2"}