{"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"}