{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EYXIZPZBOQHUYHIJNVYZ6DGIJ2","short_pith_number":"pith:EYXIZPZB","schema_version":"1.0","canonical_sha256":"262e8cbf21740f4c1d096d719f0cc84e94c4b6fa6f02a37ce3ef396dd3c15ee2","source":{"kind":"arxiv","id":"1811.10264","version":4},"attestation_state":"computed","paper":{"title":"PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Qihao Liu, Xiaofeng Liu, Yujia Wang","submitted_at":"2018-11-26T10:05:15Z","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"},"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":"1811.10264","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-26T10:05:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6e05b4be909b2faaf8a222fda454fe899ecbe3a01c05dad90e072f305effc23f","abstract_canon_sha256":"000782bdb7d5596c13983790ab88adeef784348f017977602f954c7d78cca11d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:03.783273Z","signature_b64":"Ir2JXaMU2bH29H0CEXIw/qFJKaQ5KBSRz/r6a64MRhf054jcPcbPOWxcUDoivOv9mXHiP/K1gBrY/xwJq/CYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"262e8cbf21740f4c1d096d719f0cc84e94c4b6fa6f02a37ce3ef396dd3c15ee2","last_reissued_at":"2026-07-05T03:21:03.782740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:03.782740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Qihao Liu, Xiaofeng Liu, Yujia Wang","submitted_at":"2018-11-26T10:05:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10264","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1811.10264/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1811.10264","created_at":"2026-07-05T03:21:03.782812+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.10264v4","created_at":"2026-07-05T03:21:03.782812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10264","created_at":"2026-07-05T03:21:03.782812+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYXIZPZBOQHU","created_at":"2026-07-05T03:21:03.782812+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYXIZPZBOQHUYHIJ","created_at":"2026-07-05T03:21:03.782812+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYXIZPZB","created_at":"2026-07-05T03:21:03.782812+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/EYXIZPZBOQHUYHIJNVYZ6DGIJ2","json":"https://pith.science/pith/EYXIZPZBOQHUYHIJNVYZ6DGIJ2.json","graph_json":"https://pith.science/api/pith-number/EYXIZPZBOQHUYHIJNVYZ6DGIJ2/graph.json","events_json":"https://pith.science/api/pith-number/EYXIZPZBOQHUYHIJNVYZ6DGIJ2/events.json","paper":"https://pith.science/paper/EYXIZPZB"},"agent_actions":{"view_html":"https://pith.science/pith/EYXIZPZBOQHUYHIJNVYZ6DGIJ2","download_json":"https://pith.science/pith/EYXIZPZBOQHUYHIJNVYZ6DGIJ2.json","view_paper":"https://pith.science/paper/EYXIZPZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.10264&json=true","fetch_graph":"https://pith.science/api/pith-number/EYXIZPZBOQHUYHIJNVYZ6DGIJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/EYXIZPZBOQHUYHIJNVYZ6DGIJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYXIZPZBOQHUYHIJNVYZ6DGIJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYXIZPZBOQHUYHIJNVYZ6DGIJ2/action/storage_attestation","attest_author":"https://pith.science/pith/EYXIZPZBOQHUYHIJNVYZ6DGIJ2/action/author_attestation","sign_citation":"https://pith.science/pith/EYXIZPZBOQHUYHIJNVYZ6DGIJ2/action/citation_signature","submit_replication":"https://pith.science/pith/EYXIZPZBOQHUYHIJNVYZ6DGIJ2/action/replication_record"}},"created_at":"2026-07-05T03:21:03.782812+00:00","updated_at":"2026-07-05T03:21:03.782812+00:00"}