{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UHEBMECIOD4DDGCXBMPGOCBT2D","short_pith_number":"pith:UHEBMECI","schema_version":"1.0","canonical_sha256":"a1c816104870f83198570b1e670833d0e1d1e1ad8da068a4e7f624b9228ef6f0","source":{"kind":"arxiv","id":"1809.06098","version":2},"attestation_state":"computed","paper":{"title":"Policy Optimization via Importance Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberto Maria Metelli, Francesco Faccio, Marcello Restelli, Matteo Papini","submitted_at":"2018-09-17T09:42:26Z","abstract_excerpt":"Policy optimization is an effective reinforcement learning approach to solve continuous control tasks. Recent achievements have shown that alternating online and offline optimization is a successful choice for efficient trajectory reuse. However, deciding when to stop optimizing and collect new trajectories is non-trivial, as it requires to account for the variance of the objective function estimate. In this paper, we propose a novel, model-free, policy search algorithm, POIS, applicable in both action-based and parameter-based settings. We first derive a high-confidence bound for importance s"},"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":"1809.06098","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-17T09:42:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"89cfa10c264c32c82f3087e48082381cce7c5879d2727ec9625767494ad4fbcf","abstract_canon_sha256":"3e905c782a22f814fd22805b65158764dcde2d1087b74f60860353cb1c488b66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:52.866566Z","signature_b64":"yQu3iJUMBIy6G/ThNEHN16eB3fwPyeXPusPMdUTbO9oeV6OkYAEnvccsFefIW7oUkkputtSHrCPKrTMpH28ZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1c816104870f83198570b1e670833d0e1d1e1ad8da068a4e7f624b9228ef6f0","last_reissued_at":"2026-05-18T00:01:52.866117Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:52.866117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Optimization via Importance Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberto Maria Metelli, Francesco Faccio, Marcello Restelli, Matteo Papini","submitted_at":"2018-09-17T09:42:26Z","abstract_excerpt":"Policy optimization is an effective reinforcement learning approach to solve continuous control tasks. Recent achievements have shown that alternating online and offline optimization is a successful choice for efficient trajectory reuse. However, deciding when to stop optimizing and collect new trajectories is non-trivial, as it requires to account for the variance of the objective function estimate. In this paper, we propose a novel, model-free, policy search algorithm, POIS, applicable in both action-based and parameter-based settings. We first derive a high-confidence bound for importance s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06098","kind":"arxiv","version":2},"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":"1809.06098","created_at":"2026-05-18T00:01:52.866189+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.06098v2","created_at":"2026-05-18T00:01:52.866189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06098","created_at":"2026-05-18T00:01:52.866189+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHEBMECIOD4D","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHEBMECIOD4DDGCX","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHEBMECI","created_at":"2026-05-18T12:32:56.356000+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/UHEBMECIOD4DDGCXBMPGOCBT2D","json":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D.json","graph_json":"https://pith.science/api/pith-number/UHEBMECIOD4DDGCXBMPGOCBT2D/graph.json","events_json":"https://pith.science/api/pith-number/UHEBMECIOD4DDGCXBMPGOCBT2D/events.json","paper":"https://pith.science/paper/UHEBMECI"},"agent_actions":{"view_html":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D","download_json":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D.json","view_paper":"https://pith.science/paper/UHEBMECI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.06098&json=true","fetch_graph":"https://pith.science/api/pith-number/UHEBMECIOD4DDGCXBMPGOCBT2D/graph.json","fetch_events":"https://pith.science/api/pith-number/UHEBMECIOD4DDGCXBMPGOCBT2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D/action/storage_attestation","attest_author":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D/action/author_attestation","sign_citation":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D/action/citation_signature","submit_replication":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D/action/replication_record"}},"created_at":"2026-05-18T00:01:52.866189+00:00","updated_at":"2026-05-18T00:01:52.866189+00:00"}