{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UHEBMECIOD4DDGCXBMPGOCBT2D","short_pith_number":"pith:UHEBMECI","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"},"canonical_sha256":"a1c816104870f83198570b1e670833d0e1d1e1ad8da068a4e7f624b9228ef6f0","source":{"kind":"arxiv","id":"1809.06098","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.06098","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.06098v2","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06098","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"pith_short_12","alias_value":"UHEBMECIOD4D","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UHEBMECIOD4DDGCX","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UHEBMECI","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UHEBMECIOD4DDGCXBMPGOCBT2D","target":"record","payload":{"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"},"canonical_sha256":"a1c816104870f83198570b1e670833d0e1d1e1ad8da068a4e7f624b9228ef6f0","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"},"source_kind":"arxiv","source_id":"1809.06098","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q70APApj1qtDhsv/LPmF6p97uZ8Tt21UMWIZnqu8WgZaIUFgNk/Amg6+Th/z7Kxj8UbaOvbB8sgOmpauvv00AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:08:33.674683Z"},"content_sha256":"b428c1e7613ec6fedc79f3792eb20a88e6e3878c92fa219037f744e23e8054eb","schema_version":"1.0","event_id":"sha256:b428c1e7613ec6fedc79f3792eb20a88e6e3878c92fa219037f744e23e8054eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UHEBMECIOD4DDGCXBMPGOCBT2D","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3N1/fsVeAwYBanTycP4HgF7/mBY7Tcihcakd3ZQUSPUrs0+aMGOga1xJEtPcZZ9pTWDK7fVsbhCJTxfug7c4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:08:33.675330Z"},"content_sha256":"f62d0559bfcba076dfc0c3035524679f2b4c591b1335470c63800b99e149fdce","schema_version":"1.0","event_id":"sha256:f62d0559bfcba076dfc0c3035524679f2b4c591b1335470c63800b99e149fdce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D/bundle.json","state_url":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UHEBMECIOD4DDGCXBMPGOCBT2D/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":"2026-05-27T07:08:33Z","links":{"resolver":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D","bundle":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D/bundle.json","state":"https://pith.science/pith/UHEBMECIOD4DDGCXBMPGOCBT2D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UHEBMECIOD4DDGCXBMPGOCBT2D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UHEBMECIOD4DDGCXBMPGOCBT2D","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":"3e905c782a22f814fd22805b65158764dcde2d1087b74f60860353cb1c488b66","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-17T09:42:26Z","title_canon_sha256":"89cfa10c264c32c82f3087e48082381cce7c5879d2727ec9625767494ad4fbcf"},"schema_version":"1.0","source":{"id":"1809.06098","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.06098","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.06098v2","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06098","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"pith_short_12","alias_value":"UHEBMECIOD4D","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UHEBMECIOD4DDGCX","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UHEBMECI","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:f62d0559bfcba076dfc0c3035524679f2b4c591b1335470c63800b99e149fdce","target":"graph","created_at":"2026-05-18T00:01:52Z","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":"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","authors_text":"Alberto Maria Metelli, Francesco Faccio, Marcello Restelli, Matteo Papini","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-17T09:42:26Z","title":"Policy Optimization via Importance Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06098","kind":"arxiv","version":2},"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:b428c1e7613ec6fedc79f3792eb20a88e6e3878c92fa219037f744e23e8054eb","target":"record","created_at":"2026-05-18T00:01:52Z","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":"3e905c782a22f814fd22805b65158764dcde2d1087b74f60860353cb1c488b66","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-17T09:42:26Z","title_canon_sha256":"89cfa10c264c32c82f3087e48082381cce7c5879d2727ec9625767494ad4fbcf"},"schema_version":"1.0","source":{"id":"1809.06098","kind":"arxiv","version":2}},"canonical_sha256":"a1c816104870f83198570b1e670833d0e1d1e1ad8da068a4e7f624b9228ef6f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1c816104870f83198570b1e670833d0e1d1e1ad8da068a4e7f624b9228ef6f0","first_computed_at":"2026-05-18T00:01:52.866117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:52.866117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yQu3iJUMBIy6G/ThNEHN16eB3fwPyeXPusPMdUTbO9oeV6OkYAEnvccsFefIW7oUkkputtSHrCPKrTMpH28ZDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:52.866566Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.06098","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b428c1e7613ec6fedc79f3792eb20a88e6e3878c92fa219037f744e23e8054eb","sha256:f62d0559bfcba076dfc0c3035524679f2b4c591b1335470c63800b99e149fdce"],"state_sha256":"e8c51c8a5c7f60b44387068aa26d793644e2d8aa0064228ce281adba1891277d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zSvsYovs9u7nQzdwg0HAV9aLOj/X4XYMq6GEreeOKmp2bbNV2E6HnuOTJltDGM/KZ0nIFzFSX/jox6eYMSR0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T07:08:33.678592Z","bundle_sha256":"2e85669ae1a65b0dbfd4d6889b9e5e97d930c24977517da0e80c944ce02f9182"}}