{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EYXIZPZBOQHUYHIJNVYZ6DGIJ2","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":"000782bdb7d5596c13983790ab88adeef784348f017977602f954c7d78cca11d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-26T10:05:15Z","title_canon_sha256":"6e05b4be909b2faaf8a222fda454fe899ecbe3a01c05dad90e072f305effc23f"},"schema_version":"1.0","source":{"id":"1811.10264","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10264","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10264v4","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10264","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"pith_short_12","alias_value":"EYXIZPZBOQHU","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"pith_short_16","alias_value":"EYXIZPZBOQHUYHIJ","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"pith_short_8","alias_value":"EYXIZPZB","created_at":"2026-07-05T03:21:03Z"}],"graph_snapshots":[{"event_id":"sha256:d1890eefe7dba764fa603c9010d76baf4a9c2da1f01bb1001bb11d03ef1bdeb3","target":"graph","created_at":"2026-07-05T03:21:03Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1811.10264/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has made remarkable achievements, but it still suffers from inadequate exploration strategies, sparse reward signals, and deceptive reward functions. To alleviate these problems, a Population-guided Novelty Search (PNS) parallel learning method is proposed in this paper. In PNS, the population is divided into multiple sub-populations, each of which has one chief agent and several exploring agents. The chief agent evaluates the policies learned by exploring agents and shares the optimal policy with all sub-populations. The exploring agents learn their policies in col","authors_text":"Qihao Liu, Xiaofeng Liu, Yujia Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-26T10:05:15Z","title":"PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10264","kind":"arxiv","version":4},"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:e66b1e0c55b725d685bccba87b82a600cde1b104d54973e53a085103da4df4c5","target":"record","created_at":"2026-07-05T03:21:03Z","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":"000782bdb7d5596c13983790ab88adeef784348f017977602f954c7d78cca11d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-26T10:05:15Z","title_canon_sha256":"6e05b4be909b2faaf8a222fda454fe899ecbe3a01c05dad90e072f305effc23f"},"schema_version":"1.0","source":{"id":"1811.10264","kind":"arxiv","version":4}},"canonical_sha256":"262e8cbf21740f4c1d096d719f0cc84e94c4b6fa6f02a37ce3ef396dd3c15ee2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"262e8cbf21740f4c1d096d719f0cc84e94c4b6fa6f02a37ce3ef396dd3c15ee2","first_computed_at":"2026-07-05T03:21:03.782740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:03.782740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ir2JXaMU2bH29H0CEXIw/qFJKaQ5KBSRz/r6a64MRhf054jcPcbPOWxcUDoivOv9mXHiP/K1gBrY/xwJq/CYCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:03.783273Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.10264","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e66b1e0c55b725d685bccba87b82a600cde1b104d54973e53a085103da4df4c5","sha256:d1890eefe7dba764fa603c9010d76baf4a9c2da1f01bb1001bb11d03ef1bdeb3"],"state_sha256":"74ea91955fdef07bb4ba102fc27ea80f75ca87830e3069f47d78fb9249dfface"}