{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3Y3EGH2DZTLXLCU6FZLSMIRI6X","short_pith_number":"pith:3Y3EGH2D","schema_version":"1.0","canonical_sha256":"de36431f43ccd7758a9e2e57262228f5f057ea69bdbe2a5002846e6cae6b3d34","source":{"kind":"arxiv","id":"2001.02907","version":1},"attestation_state":"computed","paper":{"title":"Population-Guided Parallel Policy Search for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Giseung Park, Whiyoung Jung, Youngchul Sung","submitted_at":"2020-01-09T10:13:57Z","abstract_excerpt":"In this paper, a new population-guided parallel learning scheme is proposed to enhance the performance of off-policy reinforcement learning (RL). In the proposed scheme, multiple identical learners with their own value-functions and policies share a common experience replay buffer, and search a good policy in collaboration with the guidance of the best policy information. The key point is that the information of the best policy is fused in a soft manner by constructing an augmented loss function for policy update to enlarge the overall search region by the multiple learners. The guidance by th"},"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":"2001.02907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-09T10:13:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b55fb5d1dce67bd20db233850341d1601f6b7ab2f5ac6bae210571d4cbf6924e","abstract_canon_sha256":"983f33d81a794b0a18b14ff685092ffe88ef0f9b4dc47e20f9a49a4e7cbe947f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:32:31.835160Z","signature_b64":"swnxFtsjBn9YJEZDktzlm3XqNPd2nEF/mQkxej2myc9rPiYGGE7QbVrRySH57Kq3JrWMzS1ETg/w6XNg1oKZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de36431f43ccd7758a9e2e57262228f5f057ea69bdbe2a5002846e6cae6b3d34","last_reissued_at":"2026-07-05T00:32:31.834770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:32:31.834770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Population-Guided Parallel Policy Search for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Giseung Park, Whiyoung Jung, Youngchul Sung","submitted_at":"2020-01-09T10:13:57Z","abstract_excerpt":"In this paper, a new population-guided parallel learning scheme is proposed to enhance the performance of off-policy reinforcement learning (RL). In the proposed scheme, multiple identical learners with their own value-functions and policies share a common experience replay buffer, and search a good policy in collaboration with the guidance of the best policy information. The key point is that the information of the best policy is fused in a soft manner by constructing an augmented loss function for policy update to enlarge the overall search region by the multiple learners. The guidance by th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.02907","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.02907/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":"2001.02907","created_at":"2026-07-05T00:32:31.834833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.02907v1","created_at":"2026-07-05T00:32:31.834833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.02907","created_at":"2026-07-05T00:32:31.834833+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Y3EGH2DZTLX","created_at":"2026-07-05T00:32:31.834833+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Y3EGH2DZTLXLCU6","created_at":"2026-07-05T00:32:31.834833+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Y3EGH2D","created_at":"2026-07-05T00:32:31.834833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.01336","citing_title":"Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3Y3EGH2DZTLXLCU6FZLSMIRI6X","json":"https://pith.science/pith/3Y3EGH2DZTLXLCU6FZLSMIRI6X.json","graph_json":"https://pith.science/api/pith-number/3Y3EGH2DZTLXLCU6FZLSMIRI6X/graph.json","events_json":"https://pith.science/api/pith-number/3Y3EGH2DZTLXLCU6FZLSMIRI6X/events.json","paper":"https://pith.science/paper/3Y3EGH2D"},"agent_actions":{"view_html":"https://pith.science/pith/3Y3EGH2DZTLXLCU6FZLSMIRI6X","download_json":"https://pith.science/pith/3Y3EGH2DZTLXLCU6FZLSMIRI6X.json","view_paper":"https://pith.science/paper/3Y3EGH2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.02907&json=true","fetch_graph":"https://pith.science/api/pith-number/3Y3EGH2DZTLXLCU6FZLSMIRI6X/graph.json","fetch_events":"https://pith.science/api/pith-number/3Y3EGH2DZTLXLCU6FZLSMIRI6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Y3EGH2DZTLXLCU6FZLSMIRI6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Y3EGH2DZTLXLCU6FZLSMIRI6X/action/storage_attestation","attest_author":"https://pith.science/pith/3Y3EGH2DZTLXLCU6FZLSMIRI6X/action/author_attestation","sign_citation":"https://pith.science/pith/3Y3EGH2DZTLXLCU6FZLSMIRI6X/action/citation_signature","submit_replication":"https://pith.science/pith/3Y3EGH2DZTLXLCU6FZLSMIRI6X/action/replication_record"}},"created_at":"2026-07-05T00:32:31.834833+00:00","updated_at":"2026-07-05T00:32:31.834833+00:00"}