{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LW47CRTR4YAMNHC2STGYKBDOB6","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":"fbfc4fffa31d76c0ba0d07d38b560a394963fc0da60e5782a25074d91e675d6f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-03T03:29:32Z","title_canon_sha256":"0c1ea0f9339fcd446cf0172748e34dc73805ddfe823530f10c24116709146e4e"},"schema_version":"1.0","source":{"id":"1711.01012","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.01012","created_at":"2026-05-18T00:21:21Z"},{"alias_kind":"arxiv_version","alias_value":"1711.01012v2","created_at":"2026-05-18T00:21:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01012","created_at":"2026-05-18T00:21:21Z"},{"alias_kind":"pith_short_12","alias_value":"LW47CRTR4YAM","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LW47CRTR4YAMNHC2","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LW47CRTR","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:e9397d8ae55efcb3f6bf132cc5fe3ec7e054bf886801e9ef325e3785bf2bea04","target":"graph","created_at":"2026-05-18T00:21:21Z","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":"Genetic algorithms have been widely used in many practical optimization problems. Inspired by natural selection, operators, including mutation, crossover and selection, provide effective heuristics for search and black-box optimization. However, they have not been shown useful for deep reinforcement learning, possibly due to the catastrophic consequence of parameter crossovers of neural networks. Here, we present Genetic Policy Optimization (GPO), a new genetic algorithm for sample-efficient deep policy optimization. GPO uses imitation learning for policy crossover in the state space and appli","authors_text":"Jian Peng, Tanmay Gangwani","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-03T03:29:32Z","title":"Policy Optimization by Genetic Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01012","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:f65ddbaeb82df09654863304094a55facc734ffd8613f9a0e6554bd1c6010e0e","target":"record","created_at":"2026-05-18T00:21:21Z","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":"fbfc4fffa31d76c0ba0d07d38b560a394963fc0da60e5782a25074d91e675d6f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-03T03:29:32Z","title_canon_sha256":"0c1ea0f9339fcd446cf0172748e34dc73805ddfe823530f10c24116709146e4e"},"schema_version":"1.0","source":{"id":"1711.01012","kind":"arxiv","version":2}},"canonical_sha256":"5db9f14671e600c69c5a94cd85046e0f9def40aac18be4a097a5b193421b0af3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5db9f14671e600c69c5a94cd85046e0f9def40aac18be4a097a5b193421b0af3","first_computed_at":"2026-05-18T00:21:21.836542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:21.836542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yCunKx48NLXGsHe0HwGIrTXVOrZ8F2VCIjSnL3Xf9UAwrfYO1iH1mkGUycXfT5+cgRDO2xBHtFGyAghSXCVYDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:21.837244Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.01012","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f65ddbaeb82df09654863304094a55facc734ffd8613f9a0e6554bd1c6010e0e","sha256:e9397d8ae55efcb3f6bf132cc5fe3ec7e054bf886801e9ef325e3785bf2bea04"],"state_sha256":"aedf462c04e8a2463bbe222eb7f335fff5dacccb7cf9661b6928ecdc5a98d740"}