{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BUDSECL37NUH3U6ZMBOEKGWC5H","short_pith_number":"pith:BUDSECL3","schema_version":"1.0","canonical_sha256":"0d0722097bfb687dd3d9605c451ac2e9fc02320883b278af55fce23347e474e3","source":{"kind":"arxiv","id":"2506.02767","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Model-Based Reinforcement Learning using Non-Linear Trajectory Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Alberto Dalla Libera, Giulio Giacomuzzo, Marco Cal\\`i, Ruggero Carli","submitted_at":"2025-06-03T11:30:59Z","abstract_excerpt":"This paper addresses the slow policy optimization convergence of Monte Carlo Probabilistic Inference for Learning Control (MC-PILCO), a state-of-the-art model-based reinforcement learning (MBRL) algorithm, by integrating it with iterative Linear Quadratic Regulator (iLQR), a fast trajectory optimization method suitable for nonlinear systems. The proposed method, Exploration-Boosted MC-PILCO (EB-MC-PILCO), leverages iLQR to generate informative, exploratory trajectories and initialize the policy, significantly reducing the number of required optimization steps. Experiments on the cart-pole task"},"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":"2506.02767","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T11:30:59Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"9e96671af21a38efc248ff9f64b586c5e369344291dba5218de7d816c9e9df2e","abstract_canon_sha256":"4f2567debffdc9fba6e66690745ceb02a31c16a1a18c85053dae1fc11a21b126"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:08.322409Z","signature_b64":"pWWKjYoljoKZIuiDWIUDT5wdTDMXMIo/PR32cqe3mj9FRyeMCzySuutVBcnJveoOKTm/VJVamZL1Z45D5HacBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d0722097bfb687dd3d9605c451ac2e9fc02320883b278af55fce23347e474e3","last_reissued_at":"2026-07-05T11:15:08.321930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:08.321930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Model-Based Reinforcement Learning using Non-Linear Trajectory Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Alberto Dalla Libera, Giulio Giacomuzzo, Marco Cal\\`i, Ruggero Carli","submitted_at":"2025-06-03T11:30:59Z","abstract_excerpt":"This paper addresses the slow policy optimization convergence of Monte Carlo Probabilistic Inference for Learning Control (MC-PILCO), a state-of-the-art model-based reinforcement learning (MBRL) algorithm, by integrating it with iterative Linear Quadratic Regulator (iLQR), a fast trajectory optimization method suitable for nonlinear systems. The proposed method, Exploration-Boosted MC-PILCO (EB-MC-PILCO), leverages iLQR to generate informative, exploratory trajectories and initialize the policy, significantly reducing the number of required optimization steps. Experiments on the cart-pole task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02767","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/2506.02767/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.02767","created_at":"2026-07-05T11:15:08.321988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02767v1","created_at":"2026-07-05T11:15:08.321988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02767","created_at":"2026-07-05T11:15:08.321988+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUDSECL37NUH","created_at":"2026-07-05T11:15:08.321988+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUDSECL37NUH3U6Z","created_at":"2026-07-05T11:15:08.321988+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUDSECL3","created_at":"2026-07-05T11:15:08.321988+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H","json":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H.json","graph_json":"https://pith.science/api/pith-number/BUDSECL37NUH3U6ZMBOEKGWC5H/graph.json","events_json":"https://pith.science/api/pith-number/BUDSECL37NUH3U6ZMBOEKGWC5H/events.json","paper":"https://pith.science/paper/BUDSECL3"},"agent_actions":{"view_html":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H","download_json":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H.json","view_paper":"https://pith.science/paper/BUDSECL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02767&json=true","fetch_graph":"https://pith.science/api/pith-number/BUDSECL37NUH3U6ZMBOEKGWC5H/graph.json","fetch_events":"https://pith.science/api/pith-number/BUDSECL37NUH3U6ZMBOEKGWC5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H/action/storage_attestation","attest_author":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H/action/author_attestation","sign_citation":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H/action/citation_signature","submit_replication":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H/action/replication_record"}},"created_at":"2026-07-05T11:15:08.321988+00:00","updated_at":"2026-07-05T11:15:08.321988+00:00"}