{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WVZ63MYJLH7GQCPCUKJKPYT4VU","short_pith_number":"pith:WVZ63MYJ","schema_version":"1.0","canonical_sha256":"b573edb30959fe6809e2a292a7e27cad09d4866d97617a308f933526b54262e1","source":{"kind":"arxiv","id":"1902.05284","version":2},"attestation_state":"computed","paper":{"title":"Learn a Prior for RHEA for Better Online Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Li, Weiming Liu, Xin Tong","submitted_at":"2019-02-14T09:56:00Z","abstract_excerpt":"Rolling Horizon Evolutionary Algorithms (RHEA) are a class of online planning methods for real-time game playing; their performance is closely related to the planning horizon and the search time allowed. In this paper, we propose to learn a prior for RHEA in an offline manner by training a value network and a policy network. The value network is used to reduce the planning horizon by providing an estimation of future rewards, and the policy network is used to initialize the population, which helps to narrow down the search scope. The proposed algorithm, named prior-based RHEA (p-RHEA), trains "},"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":"1902.05284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-14T09:56:00Z","cross_cats_sorted":[],"title_canon_sha256":"e8c8aac849ad58c4ba279f8f7346d5a6267668bac0bc88bf15eecff1d66f65e3","abstract_canon_sha256":"f123c30ab0155645ddeedc0743fe6932de9eaf3a963d7a8dbf51c92a5357b17e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:58.170231Z","signature_b64":"JNkl9kJmXgnuS6qb+f4ZUoybvDKX+rcHMZHGAhcNQlOlqCPglbVtHBIUvwWG2VdpkTfI9NDuLKo+QEFjlQt0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b573edb30959fe6809e2a292a7e27cad09d4866d97617a308f933526b54262e1","last_reissued_at":"2026-05-17T23:52:58.169536Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:58.169536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learn a Prior for RHEA for Better Online Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Li, Weiming Liu, Xin Tong","submitted_at":"2019-02-14T09:56:00Z","abstract_excerpt":"Rolling Horizon Evolutionary Algorithms (RHEA) are a class of online planning methods for real-time game playing; their performance is closely related to the planning horizon and the search time allowed. In this paper, we propose to learn a prior for RHEA in an offline manner by training a value network and a policy network. The value network is used to reduce the planning horizon by providing an estimation of future rewards, and the policy network is used to initialize the population, which helps to narrow down the search scope. The proposed algorithm, named prior-based RHEA (p-RHEA), trains "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05284","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1902.05284","created_at":"2026-05-17T23:52:58.169647+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.05284v2","created_at":"2026-05-17T23:52:58.169647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05284","created_at":"2026-05-17T23:52:58.169647+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVZ63MYJLH7G","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVZ63MYJLH7GQCPC","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVZ63MYJ","created_at":"2026-05-18T12:33:33.725879+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/WVZ63MYJLH7GQCPCUKJKPYT4VU","json":"https://pith.science/pith/WVZ63MYJLH7GQCPCUKJKPYT4VU.json","graph_json":"https://pith.science/api/pith-number/WVZ63MYJLH7GQCPCUKJKPYT4VU/graph.json","events_json":"https://pith.science/api/pith-number/WVZ63MYJLH7GQCPCUKJKPYT4VU/events.json","paper":"https://pith.science/paper/WVZ63MYJ"},"agent_actions":{"view_html":"https://pith.science/pith/WVZ63MYJLH7GQCPCUKJKPYT4VU","download_json":"https://pith.science/pith/WVZ63MYJLH7GQCPCUKJKPYT4VU.json","view_paper":"https://pith.science/paper/WVZ63MYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.05284&json=true","fetch_graph":"https://pith.science/api/pith-number/WVZ63MYJLH7GQCPCUKJKPYT4VU/graph.json","fetch_events":"https://pith.science/api/pith-number/WVZ63MYJLH7GQCPCUKJKPYT4VU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVZ63MYJLH7GQCPCUKJKPYT4VU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVZ63MYJLH7GQCPCUKJKPYT4VU/action/storage_attestation","attest_author":"https://pith.science/pith/WVZ63MYJLH7GQCPCUKJKPYT4VU/action/author_attestation","sign_citation":"https://pith.science/pith/WVZ63MYJLH7GQCPCUKJKPYT4VU/action/citation_signature","submit_replication":"https://pith.science/pith/WVZ63MYJLH7GQCPCUKJKPYT4VU/action/replication_record"}},"created_at":"2026-05-17T23:52:58.169647+00:00","updated_at":"2026-05-17T23:52:58.169647+00:00"}