{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3YG6EEYYRFCTOTM7PNIYL72P7C","short_pith_number":"pith:3YG6EEYY","schema_version":"1.0","canonical_sha256":"de0de213188945374d9f7b5185ff4ff89525156c413dddb5e6a1e2b1a582b327","source":{"kind":"arxiv","id":"1805.10662","version":3},"attestation_state":"computed","paper":{"title":"Fingerprint Policy Optimisation for Robust Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael A. Osborne, Shimon Whiteson, Supratik Paul","submitted_at":"2018-05-27T17:50:22Z","abstract_excerpt":"Policy gradient methods ignore the potential value of adjusting environment variables: unobservable state features that are randomly determined by the environment in a physical setting, but are controllable in a simulator. This can lead to slow learning, or convergence to suboptimal policies, if the environment variable has a large impact on the transition dynamics. In this paper, we present fingerprint policy optimisation (FPO), which finds a policy that is optimal in expectation across the distribution of environment variables. The central idea is to use Bayesian optimisation (BO) to activel"},"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":"1805.10662","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-27T17:50:22Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6716ddef91d061a5db1a0aea6c66ae467f3bbbdec23fef1257bedb49c9b74927","abstract_canon_sha256":"a43c9d855ad20fb776c3722578edfe9e9158a0673df283a4c6f705625889e940"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:04.673706Z","signature_b64":"v7OezX5io5Yhfc1GoYyp0/A1JmbAFNucRLwhEOS3ksYcFDshlNVkxrNJs1TpnlZCq0jPdR7Oax1Jo6ldptFrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de0de213188945374d9f7b5185ff4ff89525156c413dddb5e6a1e2b1a582b327","last_reissued_at":"2026-05-17T23:45:04.673050Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:04.673050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fingerprint Policy Optimisation for Robust Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael A. Osborne, Shimon Whiteson, Supratik Paul","submitted_at":"2018-05-27T17:50:22Z","abstract_excerpt":"Policy gradient methods ignore the potential value of adjusting environment variables: unobservable state features that are randomly determined by the environment in a physical setting, but are controllable in a simulator. This can lead to slow learning, or convergence to suboptimal policies, if the environment variable has a large impact on the transition dynamics. In this paper, we present fingerprint policy optimisation (FPO), which finds a policy that is optimal in expectation across the distribution of environment variables. The central idea is to use Bayesian optimisation (BO) to activel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10662","kind":"arxiv","version":3},"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":"1805.10662","created_at":"2026-05-17T23:45:04.673167+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.10662v3","created_at":"2026-05-17T23:45:04.673167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10662","created_at":"2026-05-17T23:45:04.673167+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YG6EEYYRFCT","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YG6EEYYRFCTOTM7","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YG6EEYY","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.01475","citing_title":"Generalizing from a few environments in safety-critical reinforcement learning","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YG6EEYYRFCTOTM7PNIYL72P7C","json":"https://pith.science/pith/3YG6EEYYRFCTOTM7PNIYL72P7C.json","graph_json":"https://pith.science/api/pith-number/3YG6EEYYRFCTOTM7PNIYL72P7C/graph.json","events_json":"https://pith.science/api/pith-number/3YG6EEYYRFCTOTM7PNIYL72P7C/events.json","paper":"https://pith.science/paper/3YG6EEYY"},"agent_actions":{"view_html":"https://pith.science/pith/3YG6EEYYRFCTOTM7PNIYL72P7C","download_json":"https://pith.science/pith/3YG6EEYYRFCTOTM7PNIYL72P7C.json","view_paper":"https://pith.science/paper/3YG6EEYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.10662&json=true","fetch_graph":"https://pith.science/api/pith-number/3YG6EEYYRFCTOTM7PNIYL72P7C/graph.json","fetch_events":"https://pith.science/api/pith-number/3YG6EEYYRFCTOTM7PNIYL72P7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YG6EEYYRFCTOTM7PNIYL72P7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YG6EEYYRFCTOTM7PNIYL72P7C/action/storage_attestation","attest_author":"https://pith.science/pith/3YG6EEYYRFCTOTM7PNIYL72P7C/action/author_attestation","sign_citation":"https://pith.science/pith/3YG6EEYYRFCTOTM7PNIYL72P7C/action/citation_signature","submit_replication":"https://pith.science/pith/3YG6EEYYRFCTOTM7PNIYL72P7C/action/replication_record"}},"created_at":"2026-05-17T23:45:04.673167+00:00","updated_at":"2026-05-17T23:45:04.673167+00:00"}