{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WMX2PAAJ5STN3TKJDZA43GH65L","short_pith_number":"pith:WMX2PAAJ","schema_version":"1.0","canonical_sha256":"b32fa78009eca6ddcd491e41cd98feeadd220d92da61d22ef73bd7cbc0e4c3b6","source":{"kind":"arxiv","id":"1703.01250","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1703.01250","created_at":"2026-05-18T00:34:41.847937+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.01250v1","created_at":"2026-05-18T00:34:41.847937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01250","created_at":"2026-05-18T00:34:41.847937+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMX2PAAJ5STN","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMX2PAAJ5STN3TKJ","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMX2PAAJ","created_at":"2026-05-18T12:31:53.515858+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/WMX2PAAJ5STN3TKJDZA43GH65L","json":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L.json","graph_json":"https://pith.science/api/pith-number/WMX2PAAJ5STN3TKJDZA43GH65L/graph.json","events_json":"https://pith.science/api/pith-number/WMX2PAAJ5STN3TKJDZA43GH65L/events.json","paper":"https://pith.science/paper/WMX2PAAJ"},"agent_actions":{"view_html":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L","download_json":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L.json","view_paper":"https://pith.science/paper/WMX2PAAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.01250&json=true","fetch_graph":"https://pith.science/api/pith-number/WMX2PAAJ5STN3TKJDZA43GH65L/graph.json","fetch_events":"https://pith.science/api/pith-number/WMX2PAAJ5STN3TKJDZA43GH65L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L/action/storage_attestation","attest_author":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L/action/author_attestation","sign_citation":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L/action/citation_signature","submit_replication":"https://pith.science/pith/WMX2PAAJ5STN3TKJDZA43GH65L/action/replication_record"}},"created_at":"2026-05-18T00:34:41.847937+00:00","updated_at":"2026-05-18T00:34:41.847937+00:00"}