{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BUDSECL37NUH3U6ZMBOEKGWC5H","short_pith_number":"pith:BUDSECL3","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"},"canonical_sha256":"0d0722097bfb687dd3d9605c451ac2e9fc02320883b278af55fce23347e474e3","source":{"kind":"arxiv","id":"2506.02767","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02767","created_at":"2026-07-05T11:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02767v1","created_at":"2026-07-05T11:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02767","created_at":"2026-07-05T11:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"BUDSECL37NUH","created_at":"2026-07-05T11:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"BUDSECL37NUH3U6Z","created_at":"2026-07-05T11:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"BUDSECL3","created_at":"2026-07-05T11:15:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BUDSECL37NUH3U6ZMBOEKGWC5H","target":"record","payload":{"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"},"canonical_sha256":"0d0722097bfb687dd3d9605c451ac2e9fc02320883b278af55fce23347e474e3","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"},"source_kind":"arxiv","source_id":"2506.02767","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":"2026-07-05T11:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rBzu20o75qawndIkqfr0QDRe0gJaHut5mFI+w5BP9NpkQEi/n9Z5CG4HaGqblKoaRw/zeFH74UaV0n6vTljsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T13:53:21.157754Z"},"content_sha256":"d33a11805628e9f01eab5f5e80d3f3816cc54cab1e78299710f784c160f0d328","schema_version":"1.0","event_id":"sha256:d33a11805628e9f01eab5f5e80d3f3816cc54cab1e78299710f784c160f0d328"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BUDSECL37NUH3U6ZMBOEKGWC5H","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Z23qPvDjbcYSYE2ea3z4rEy4NT8PK9w4WwVHd4+nKzm+5xo4Z8A/MnhMizrBLfvNi4a8BbWNCYVFqwioBRdBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T13:53:21.158340Z"},"content_sha256":"01bb0ec9bbe0f34e54a714f58d9fed1666574ce81056513e467de4b3136b67c4","schema_version":"1.0","event_id":"sha256:01bb0ec9bbe0f34e54a714f58d9fed1666574ce81056513e467de4b3136b67c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H/bundle.json","state_url":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BUDSECL37NUH3U6ZMBOEKGWC5H/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":"2026-08-15T13:53:21Z","links":{"resolver":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H","bundle":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H/bundle.json","state":"https://pith.science/pith/BUDSECL37NUH3U6ZMBOEKGWC5H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BUDSECL37NUH3U6ZMBOEKGWC5H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BUDSECL37NUH3U6ZMBOEKGWC5H","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":"4f2567debffdc9fba6e66690745ceb02a31c16a1a18c85053dae1fc11a21b126","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T11:30:59Z","title_canon_sha256":"9e96671af21a38efc248ff9f64b586c5e369344291dba5218de7d816c9e9df2e"},"schema_version":"1.0","source":{"id":"2506.02767","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02767","created_at":"2026-07-05T11:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02767v1","created_at":"2026-07-05T11:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02767","created_at":"2026-07-05T11:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"BUDSECL37NUH","created_at":"2026-07-05T11:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"BUDSECL37NUH3U6Z","created_at":"2026-07-05T11:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"BUDSECL3","created_at":"2026-07-05T11:15:08Z"}],"graph_snapshots":[{"event_id":"sha256:01bb0ec9bbe0f34e54a714f58d9fed1666574ce81056513e467de4b3136b67c4","target":"graph","created_at":"2026-07-05T11:15:08Z","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/2506.02767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alberto Dalla Libera, Giulio Giacomuzzo, Marco Cal\\`i, Ruggero Carli","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T11:30:59Z","title":"Accelerating Model-Based Reinforcement Learning using Non-Linear Trajectory Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02767","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:d33a11805628e9f01eab5f5e80d3f3816cc54cab1e78299710f784c160f0d328","target":"record","created_at":"2026-07-05T11:15:08Z","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":"4f2567debffdc9fba6e66690745ceb02a31c16a1a18c85053dae1fc11a21b126","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T11:30:59Z","title_canon_sha256":"9e96671af21a38efc248ff9f64b586c5e369344291dba5218de7d816c9e9df2e"},"schema_version":"1.0","source":{"id":"2506.02767","kind":"arxiv","version":1}},"canonical_sha256":"0d0722097bfb687dd3d9605c451ac2e9fc02320883b278af55fce23347e474e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d0722097bfb687dd3d9605c451ac2e9fc02320883b278af55fce23347e474e3","first_computed_at":"2026-07-05T11:15:08.321930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:08.321930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pWWKjYoljoKZIuiDWIUDT5wdTDMXMIo/PR32cqe3mj9FRyeMCzySuutVBcnJveoOKTm/VJVamZL1Z45D5HacBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:08.322409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02767","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d33a11805628e9f01eab5f5e80d3f3816cc54cab1e78299710f784c160f0d328","sha256:01bb0ec9bbe0f34e54a714f58d9fed1666574ce81056513e467de4b3136b67c4"],"state_sha256":"f5fe07958037eb7c5a3a5a11796baad4c3cfded6b39fdb3c171642bd247d2afa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CaUzoPZ6VEtgWpyAf3D+jbuW5b5GWr1xBI3AufWLcP4rraMcxkP9KIs7FQBWd39bGqVD0ETJ5e6fMz4/8Aa6Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T13:53:21.162171Z","bundle_sha256":"088b9bf514972f6cf190c91d07c6887a1b0249de7a150c5db2d35db77a53521a"}}