{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3XYWNYZ3A5VO2EEARLH7XXGMC5","short_pith_number":"pith:3XYWNYZ3","canonical_record":{"source":{"id":"2101.12115","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-28T17:01:15Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"b2756f7797c4f4c82d3e67bd11727a40da42870a478f2f9ca2a335c9efe59ffd","abstract_canon_sha256":"1047143fe9e9a6b7fb7638ae823f30fa15b606a309c03997f4c3a9aad4e5aba0"},"schema_version":"1.0"},"canonical_sha256":"ddf166e33b076aed10808acffbdccc175b507a4033793fa24b88ea608d030be5","source":{"kind":"arxiv","id":"2101.12115","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.12115","created_at":"2026-07-05T05:19:50Z"},{"alias_kind":"arxiv_version","alias_value":"2101.12115v4","created_at":"2026-07-05T05:19:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.12115","created_at":"2026-07-05T05:19:50Z"},{"alias_kind":"pith_short_12","alias_value":"3XYWNYZ3A5VO","created_at":"2026-07-05T05:19:50Z"},{"alias_kind":"pith_short_16","alias_value":"3XYWNYZ3A5VO2EEA","created_at":"2026-07-05T05:19:50Z"},{"alias_kind":"pith_short_8","alias_value":"3XYWNYZ3","created_at":"2026-07-05T05:19:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3XYWNYZ3A5VO2EEARLH7XXGMC5","target":"record","payload":{"canonical_record":{"source":{"id":"2101.12115","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-28T17:01:15Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"b2756f7797c4f4c82d3e67bd11727a40da42870a478f2f9ca2a335c9efe59ffd","abstract_canon_sha256":"1047143fe9e9a6b7fb7638ae823f30fa15b606a309c03997f4c3a9aad4e5aba0"},"schema_version":"1.0"},"canonical_sha256":"ddf166e33b076aed10808acffbdccc175b507a4033793fa24b88ea608d030be5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:50.700167Z","signature_b64":"RaSvagSWs5mUA/hIP6zOgjqyXV1gDNLPubO9GA0VfrWUze8ltozyXfpfI9dfaNdR8TWUDdTWSHQWiPjpeejECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddf166e33b076aed10808acffbdccc175b507a4033793fa24b88ea608d030be5","last_reissued_at":"2026-07-05T05:19:50.699768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:50.699768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.12115","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:19:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dy0/Z4YSvruwE0qfPqnAKHEKhyUjVSuTUs4HLjAjPru236dNSehtvWQbSQPLF2pGE9pPw1RD8ZrJtieTtLgTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:02:37.656407Z"},"content_sha256":"7c98bae87ea61c1f65409638439c33b8e1ada12a9baa6ea09239389a9edb3e51","schema_version":"1.0","event_id":"sha256:7c98bae87ea61c1f65409638439c33b8e1ada12a9baa6ea09239389a9edb3e51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3XYWNYZ3A5VO2EEARLH7XXGMC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-Based Policy Search Using Monte Carlo Gradient Estimation with Real Systems Application","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Alberto Dalla Libera, Daniel Nikovski, Diego Romeres, Fabio Amadio, Riccardo Antonello, Ruggero Carli","submitted_at":"2021-01-28T17:01:15Z","abstract_excerpt":"In this paper, we present a Model-Based Reinforcement Learning (MBRL) algorithm named \\emph{Monte Carlo Probabilistic Inference for Learning COntrol} (MC-PILCO). The algorithm relies on Gaussian Processes (GPs) to model the system dynamics and on a Monte Carlo approach to estimate the policy gradient. This defines a framework in which we ablate the choice of the following components: (i) the selection of the cost function, (ii) the optimization of policies using dropout, (iii) an improved data efficiency through the use of structured kernels in the GP models. The combination of the aforementio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.12115","kind":"arxiv","version":4},"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/2101.12115/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":"2026-07-05T05:19:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sxqT4LZb1NGYkY0RvMNmBSeXA7fkA/bbHPcF5GMLsJQxqOdJr7oTRDEhE94gIcvT9fiitFiZya1lQZFNR6Z2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:02:37.656927Z"},"content_sha256":"206a0c6434af358c42ff08148226c6e08c7dd97c941878c3ddd141262b1b4031","schema_version":"1.0","event_id":"sha256:206a0c6434af358c42ff08148226c6e08c7dd97c941878c3ddd141262b1b4031"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3XYWNYZ3A5VO2EEARLH7XXGMC5/bundle.json","state_url":"https://pith.science/pith/3XYWNYZ3A5VO2EEARLH7XXGMC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3XYWNYZ3A5VO2EEARLH7XXGMC5/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":"2026-08-18T03:02:37Z","links":{"resolver":"https://pith.science/pith/3XYWNYZ3A5VO2EEARLH7XXGMC5","bundle":"https://pith.science/pith/3XYWNYZ3A5VO2EEARLH7XXGMC5/bundle.json","state":"https://pith.science/pith/3XYWNYZ3A5VO2EEARLH7XXGMC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3XYWNYZ3A5VO2EEARLH7XXGMC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3XYWNYZ3A5VO2EEARLH7XXGMC5","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":"1047143fe9e9a6b7fb7638ae823f30fa15b606a309c03997f4c3a9aad4e5aba0","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-28T17:01:15Z","title_canon_sha256":"b2756f7797c4f4c82d3e67bd11727a40da42870a478f2f9ca2a335c9efe59ffd"},"schema_version":"1.0","source":{"id":"2101.12115","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.12115","created_at":"2026-07-05T05:19:50Z"},{"alias_kind":"arxiv_version","alias_value":"2101.12115v4","created_at":"2026-07-05T05:19:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.12115","created_at":"2026-07-05T05:19:50Z"},{"alias_kind":"pith_short_12","alias_value":"3XYWNYZ3A5VO","created_at":"2026-07-05T05:19:50Z"},{"alias_kind":"pith_short_16","alias_value":"3XYWNYZ3A5VO2EEA","created_at":"2026-07-05T05:19:50Z"},{"alias_kind":"pith_short_8","alias_value":"3XYWNYZ3","created_at":"2026-07-05T05:19:50Z"}],"graph_snapshots":[{"event_id":"sha256:206a0c6434af358c42ff08148226c6e08c7dd97c941878c3ddd141262b1b4031","target":"graph","created_at":"2026-07-05T05:19:50Z","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/2101.12115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a Model-Based Reinforcement Learning (MBRL) algorithm named \\emph{Monte Carlo Probabilistic Inference for Learning COntrol} (MC-PILCO). The algorithm relies on Gaussian Processes (GPs) to model the system dynamics and on a Monte Carlo approach to estimate the policy gradient. This defines a framework in which we ablate the choice of the following components: (i) the selection of the cost function, (ii) the optimization of policies using dropout, (iii) an improved data efficiency through the use of structured kernels in the GP models. The combination of the aforementio","authors_text":"Alberto Dalla Libera, Daniel Nikovski, Diego Romeres, Fabio Amadio, Riccardo Antonello, Ruggero Carli","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-28T17:01:15Z","title":"Model-Based Policy Search Using Monte Carlo Gradient Estimation with Real Systems Application"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.12115","kind":"arxiv","version":4},"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":"sha256:7c98bae87ea61c1f65409638439c33b8e1ada12a9baa6ea09239389a9edb3e51","target":"record","created_at":"2026-07-05T05:19:50Z","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":"1047143fe9e9a6b7fb7638ae823f30fa15b606a309c03997f4c3a9aad4e5aba0","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-28T17:01:15Z","title_canon_sha256":"b2756f7797c4f4c82d3e67bd11727a40da42870a478f2f9ca2a335c9efe59ffd"},"schema_version":"1.0","source":{"id":"2101.12115","kind":"arxiv","version":4}},"canonical_sha256":"ddf166e33b076aed10808acffbdccc175b507a4033793fa24b88ea608d030be5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddf166e33b076aed10808acffbdccc175b507a4033793fa24b88ea608d030be5","first_computed_at":"2026-07-05T05:19:50.699768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:50.699768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RaSvagSWs5mUA/hIP6zOgjqyXV1gDNLPubO9GA0VfrWUze8ltozyXfpfI9dfaNdR8TWUDdTWSHQWiPjpeejECA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:50.700167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.12115","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c98bae87ea61c1f65409638439c33b8e1ada12a9baa6ea09239389a9edb3e51","sha256:206a0c6434af358c42ff08148226c6e08c7dd97c941878c3ddd141262b1b4031"],"state_sha256":"8bd86a704a299cb5525210bd1d785f0f8d4693d5aa0b8ed3371fe6c0d5d20d25"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SnMAPFFHDNwhi1KM4wzy4epZMzTsMadB3jz/0c0A5zCRTA7U9o7T6CkvXG065D89UNo9XrbkFM0Oa4SObIKGCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T03:02:37.662387Z","bundle_sha256":"229074637d951b7770fdc927a35fe7a94cd26927ccb9f43e6898c6b761601753"}}