{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WMX2PAAJ5STN3TKJDZA43GH65L","short_pith_number":"pith:WMX2PAAJ","canonical_record":{"source":{"id":"1703.01250","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-03T17:20:09Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"e04363a4be33407b36e770cd46f1e9ec55ee6632575d7572a44be86e330e5327","abstract_canon_sha256":"f44acdaa4d6ec163e4dbcbf907b414daf0311245930fac17deeb2611c1a456cb"},"schema_version":"1.0"},"canonical_sha256":"b32fa78009eca6ddcd491e41cd98feeadd220d92da61d22ef73bd7cbc0e4c3b6","source":{"kind":"arxiv","id":"1703.01250","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01250","created_at":"2026-05-18T00:34:41Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01250v1","created_at":"2026-05-18T00:34:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01250","created_at":"2026-05-18T00:34:41Z"},{"alias_kind":"pith_short_12","alias_value":"WMX2PAAJ5STN","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WMX2PAAJ5STN3TKJ","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WMX2PAAJ","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WMX2PAAJ5STN3TKJDZA43GH65L","target":"record","payload":{"canonical_record":{"source":{"id":"1703.01250","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-03T17:20:09Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"e04363a4be33407b36e770cd46f1e9ec55ee6632575d7572a44be86e330e5327","abstract_canon_sha256":"f44acdaa4d6ec163e4dbcbf907b414daf0311245930fac17deeb2611c1a456cb"},"schema_version":"1.0"},"canonical_sha256":"b32fa78009eca6ddcd491e41cd98feeadd220d92da61d22ef73bd7cbc0e4c3b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:41.848499Z","signature_b64":"FHUhIyO4GmL0hpB9xdLbLw9ssgQhGX4utEYjnzA8l9K54a+SRn4D3cCLDG90H0wksDNwmkKHaV4c1wAbOm1qDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b32fa78009eca6ddcd491e41cd98feeadd220d92da61d22ef73bd7cbc0e4c3b6","last_reissued_at":"2026-05-18T00:34:41.847815Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:41.847815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.01250","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":"2026-05-18T00:34:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TvxDo9k5zmWvU+g364XwrErZNqFvX4zfqAIm7r2XZITuYxsDTUXsERDA8qPVK/b8QT+3eHpJGs+fGW9v3IN+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T03:33:56.697384Z"},"content_sha256":"cc6733566d1551792e114d5be26ab6d88f9634f8baa5f4000c4f44b92298a333","schema_version":"1.0","event_id":"sha256:cc6733566d1551792e114d5be26ab6d88f9634f8baa5f4000c4f44b92298a333"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WMX2PAAJ5STN3TKJDZA43GH65L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"cs.RO","authors_text":"Alonso Marco, Andreas Krause, Angela P. Schoellig, Felix Berkenkamp, Philipp Hennig, Sebastian Trimpe, Stefan Schaal","submitted_at":"2017-03-03T17:20:09Z","abstract_excerpt":"In practice, the parameters of control policies are often tuned manually. This is time-consuming and frustrating. Reinforcement learning is a promising alternative that aims to automate this process, yet often requires too many experiments to be practical. In this paper, we propose a solution to this problem by exploiting prior knowledge from simulations, which are readily available for most robotic platforms. Specifically, we extend Entropy Search, a Bayesian optimization algorithm that maximizes information gain from each experiment, to the case of multiple information sources. The result is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01250","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":""},"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":"2026-05-18T00:34:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"drcd2siuegecUA/oxdclpdKlxXZ6JPGhn7XWWE03dxnSaEit8ud3c4e8492AwbPsKJhnH8PEcmKQGCyLwSCFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T03:33:56.698064Z"},"content_sha256":"77b2bb7f51d76ca45b254fb80a97e71e88e56d4e0340961d91b982b90919a688","schema_version":"1.0","event_id":"sha256:77b2bb7f51d76ca45b254fb80a97e71e88e56d4e0340961d91b982b90919a688"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L/bundle.json","state_url":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WMX2PAAJ5STN3TKJDZA43GH65L/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":"2026-05-27T03:33:56Z","links":{"resolver":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L","bundle":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L/bundle.json","state":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WMX2PAAJ5STN3TKJDZA43GH65L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WMX2PAAJ5STN3TKJDZA43GH65L","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":"f44acdaa4d6ec163e4dbcbf907b414daf0311245930fac17deeb2611c1a456cb","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-03T17:20:09Z","title_canon_sha256":"e04363a4be33407b36e770cd46f1e9ec55ee6632575d7572a44be86e330e5327"},"schema_version":"1.0","source":{"id":"1703.01250","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01250","created_at":"2026-05-18T00:34:41Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01250v1","created_at":"2026-05-18T00:34:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01250","created_at":"2026-05-18T00:34:41Z"},{"alias_kind":"pith_short_12","alias_value":"WMX2PAAJ5STN","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WMX2PAAJ5STN3TKJ","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WMX2PAAJ","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:77b2bb7f51d76ca45b254fb80a97e71e88e56d4e0340961d91b982b90919a688","target":"graph","created_at":"2026-05-18T00:34:41Z","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":"In practice, the parameters of control policies are often tuned manually. This is time-consuming and frustrating. Reinforcement learning is a promising alternative that aims to automate this process, yet often requires too many experiments to be practical. In this paper, we propose a solution to this problem by exploiting prior knowledge from simulations, which are readily available for most robotic platforms. Specifically, we extend Entropy Search, a Bayesian optimization algorithm that maximizes information gain from each experiment, to the case of multiple information sources. The result is","authors_text":"Alonso Marco, Andreas Krause, Angela P. Schoellig, Felix Berkenkamp, Philipp Hennig, Sebastian Trimpe, Stefan Schaal","cross_cats":["cs.LG","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-03T17:20:09Z","title":"Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01250","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:cc6733566d1551792e114d5be26ab6d88f9634f8baa5f4000c4f44b92298a333","target":"record","created_at":"2026-05-18T00:34:41Z","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":"f44acdaa4d6ec163e4dbcbf907b414daf0311245930fac17deeb2611c1a456cb","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-03T17:20:09Z","title_canon_sha256":"e04363a4be33407b36e770cd46f1e9ec55ee6632575d7572a44be86e330e5327"},"schema_version":"1.0","source":{"id":"1703.01250","kind":"arxiv","version":1}},"canonical_sha256":"b32fa78009eca6ddcd491e41cd98feeadd220d92da61d22ef73bd7cbc0e4c3b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b32fa78009eca6ddcd491e41cd98feeadd220d92da61d22ef73bd7cbc0e4c3b6","first_computed_at":"2026-05-18T00:34:41.847815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:41.847815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FHUhIyO4GmL0hpB9xdLbLw9ssgQhGX4utEYjnzA8l9K54a+SRn4D3cCLDG90H0wksDNwmkKHaV4c1wAbOm1qDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:41.848499Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.01250","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc6733566d1551792e114d5be26ab6d88f9634f8baa5f4000c4f44b92298a333","sha256:77b2bb7f51d76ca45b254fb80a97e71e88e56d4e0340961d91b982b90919a688"],"state_sha256":"decf6e8421f1519c073500f530b98036fb80045f135afa86a71eef1a11be58fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MwTdIiUmCneRUazJBVQPB8eXH0+bIx9v7TUOzFGWQM4GyDFgW7v2CisJlR3HHo7705TYkacqA3LrgKgjq6hICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T03:33:56.701537Z","bundle_sha256":"0947f373504f9e1bf88dedda05229f427bbbcf3f6afa918f880f10df1e4b71a1"}}