{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:OUQWTZLYJ3ETFIXOXEEPOV4CTB","short_pith_number":"pith:OUQWTZLY","canonical_record":{"source":{"id":"1208.4773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2012-08-23T14:48:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c9c3f7a3a23ec7e3786cb4dd7e02542dcb81e6914aab085e51fff6a2c179c56e","abstract_canon_sha256":"87883d229ebb6a83f6891c5416339ff164683f31889eb3acf8b5f94553abfe78"},"schema_version":"1.0"},"canonical_sha256":"752169e5784ec932a2eeb908f7578298705bfcb03fb3bee886b70e76073f9bb0","source":{"kind":"arxiv","id":"1208.4773","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1208.4773","created_at":"2026-05-18T02:21:00Z"},{"alias_kind":"arxiv_version","alias_value":"1208.4773v1","created_at":"2026-05-18T02:21:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1208.4773","created_at":"2026-05-18T02:21:00Z"},{"alias_kind":"pith_short_12","alias_value":"OUQWTZLYJ3ET","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_16","alias_value":"OUQWTZLYJ3ETFIXO","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_8","alias_value":"OUQWTZLY","created_at":"2026-05-18T12:27:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:OUQWTZLYJ3ETFIXOXEEPOV4CTB","target":"record","payload":{"canonical_record":{"source":{"id":"1208.4773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2012-08-23T14:48:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c9c3f7a3a23ec7e3786cb4dd7e02542dcb81e6914aab085e51fff6a2c179c56e","abstract_canon_sha256":"87883d229ebb6a83f6891c5416339ff164683f31889eb3acf8b5f94553abfe78"},"schema_version":"1.0"},"canonical_sha256":"752169e5784ec932a2eeb908f7578298705bfcb03fb3bee886b70e76073f9bb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:21:00.531161Z","signature_b64":"ydPMYdX2+zuVvZ1SlrW7FdRam5prG+eHggWsY1BsGn0Tsh6CGwzv19Frhtw33YNr1Wed1O3X8pnpg9NC1eWoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"752169e5784ec932a2eeb908f7578298705bfcb03fb3bee886b70e76073f9bb0","last_reissued_at":"2026-05-18T02:21:00.530667Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:21:00.530667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1208.4773","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:21:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hojBfYNLhefYtO4IEdRe/xi0t3aPYAeg3HPh98u7M+u1Q6Nhbze/8GkAkEpGMY/eaDM8hhjLMA7YW8fvl5Q9AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T11:43:29.155342Z"},"content_sha256":"d09a9536ab172b1f4a9321b47e7342e7fcb2322e731256f11abb785df3ebb4aa","schema_version":"1.0","event_id":"sha256:d09a9536ab172b1f4a9321b47e7342e7fcb2322e731256f11abb785df3ebb4aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:OUQWTZLYJ3ETFIXOXEEPOV4CTB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimized Look-Ahead Tree Policies: A Bridge Between Look-Ahead Tree Policies and Direct Policy Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SY","authors_text":"Damien Ernst, Francis Maes, Louis Wehenkel, Tobias Jung","submitted_at":"2012-08-23T14:48:52Z","abstract_excerpt":"Direct policy search (DPS) and look-ahead tree (LT) policies are two widely used classes of techniques to produce high performance policies for sequential decision-making problems. To make DPS approaches work well, one crucial issue is to select an appropriate space of parameterized policies with respect to the targeted problem. A fundamental issue in LT approaches is that, to take good decisions, such policies must develop very large look-ahead trees which may require excessive online computational resources. In this paper, we propose a new hybrid policy learning scheme that lies at the inter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1208.4773","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:21:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YuKuzrcuY76uDhj+netHdcJZyQ+WOtmxBnmCPLctdCvF4wO+TLdSZCjYnAeT96g3otur30O143f4v1LZKXTRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T11:43:29.155678Z"},"content_sha256":"8b5b6a0ee4b034d35c16304422266f51d240709fddfa0408c556bbdb4c343176","schema_version":"1.0","event_id":"sha256:8b5b6a0ee4b034d35c16304422266f51d240709fddfa0408c556bbdb4c343176"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUQWTZLYJ3ETFIXOXEEPOV4CTB/bundle.json","state_url":"https://pith.science/pith/OUQWTZLYJ3ETFIXOXEEPOV4CTB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUQWTZLYJ3ETFIXOXEEPOV4CTB/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":"2026-06-22T11:43:29Z","links":{"resolver":"https://pith.science/pith/OUQWTZLYJ3ETFIXOXEEPOV4CTB","bundle":"https://pith.science/pith/OUQWTZLYJ3ETFIXOXEEPOV4CTB/bundle.json","state":"https://pith.science/pith/OUQWTZLYJ3ETFIXOXEEPOV4CTB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUQWTZLYJ3ETFIXOXEEPOV4CTB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:OUQWTZLYJ3ETFIXOXEEPOV4CTB","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":"87883d229ebb6a83f6891c5416339ff164683f31889eb3acf8b5f94553abfe78","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2012-08-23T14:48:52Z","title_canon_sha256":"c9c3f7a3a23ec7e3786cb4dd7e02542dcb81e6914aab085e51fff6a2c179c56e"},"schema_version":"1.0","source":{"id":"1208.4773","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1208.4773","created_at":"2026-05-18T02:21:00Z"},{"alias_kind":"arxiv_version","alias_value":"1208.4773v1","created_at":"2026-05-18T02:21:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1208.4773","created_at":"2026-05-18T02:21:00Z"},{"alias_kind":"pith_short_12","alias_value":"OUQWTZLYJ3ET","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_16","alias_value":"OUQWTZLYJ3ETFIXO","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_8","alias_value":"OUQWTZLY","created_at":"2026-05-18T12:27:16Z"}],"graph_snapshots":[{"event_id":"sha256:8b5b6a0ee4b034d35c16304422266f51d240709fddfa0408c556bbdb4c343176","target":"graph","created_at":"2026-05-18T02:21:00Z","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":"Direct policy search (DPS) and look-ahead tree (LT) policies are two widely used classes of techniques to produce high performance policies for sequential decision-making problems. To make DPS approaches work well, one crucial issue is to select an appropriate space of parameterized policies with respect to the targeted problem. A fundamental issue in LT approaches is that, to take good decisions, such policies must develop very large look-ahead trees which may require excessive online computational resources. In this paper, we propose a new hybrid policy learning scheme that lies at the inter","authors_text":"Damien Ernst, Francis Maes, Louis Wehenkel, Tobias Jung","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2012-08-23T14:48:52Z","title":"Optimized Look-Ahead Tree Policies: A Bridge Between Look-Ahead Tree Policies and Direct Policy Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1208.4773","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:d09a9536ab172b1f4a9321b47e7342e7fcb2322e731256f11abb785df3ebb4aa","target":"record","created_at":"2026-05-18T02:21:00Z","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":"87883d229ebb6a83f6891c5416339ff164683f31889eb3acf8b5f94553abfe78","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2012-08-23T14:48:52Z","title_canon_sha256":"c9c3f7a3a23ec7e3786cb4dd7e02542dcb81e6914aab085e51fff6a2c179c56e"},"schema_version":"1.0","source":{"id":"1208.4773","kind":"arxiv","version":1}},"canonical_sha256":"752169e5784ec932a2eeb908f7578298705bfcb03fb3bee886b70e76073f9bb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"752169e5784ec932a2eeb908f7578298705bfcb03fb3bee886b70e76073f9bb0","first_computed_at":"2026-05-18T02:21:00.530667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:21:00.530667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ydPMYdX2+zuVvZ1SlrW7FdRam5prG+eHggWsY1BsGn0Tsh6CGwzv19Frhtw33YNr1Wed1O3X8pnpg9NC1eWoAg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:21:00.531161Z","signed_message":"canonical_sha256_bytes"},"source_id":"1208.4773","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d09a9536ab172b1f4a9321b47e7342e7fcb2322e731256f11abb785df3ebb4aa","sha256:8b5b6a0ee4b034d35c16304422266f51d240709fddfa0408c556bbdb4c343176"],"state_sha256":"9d2b09bd32bdc50de4d8b5737ed029340f62bb1309663bbb68d8077e0e7dbf06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FPbeEEYellJnW+dvfzprOpkuyWWD4fIL8QAAITdVOE+dSG5m79hEP7pYawUg2ThkemhpRIqF1uebG3TZsr4oCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-22T11:43:29.157494Z","bundle_sha256":"4323253b00c967d765d24fd81f684f7f80dc274799aecd1218b2c14e19a31196"}}