{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PED6KCRBTBLRKSFWXZDAX4HOX2","short_pith_number":"pith:PED6KCRB","schema_version":"1.0","canonical_sha256":"7907e50a2198571548b6be460bf0eebebed930e553419edfbdfa6c864b652f10","source":{"kind":"arxiv","id":"2002.05229","version":1},"attestation_state":"computed","paper":{"title":"Data Efficient Training for Reinforcement Learning with Adaptive Behavior Policy Sharing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ang Li, Craig Boutilier, Ed Chi, Ge Liu, Heng-Tze Cheng, Jayden Ooi, Jing Wang, Lihong Li, Rui Wu, Wai Lok Sibon Li","submitted_at":"2020-02-12T20:35:31Z","abstract_excerpt":"Deep Reinforcement Learning (RL) is proven powerful for decision making in simulated environments. However, training deep RL model is challenging in real world applications such as production-scale health-care or recommender systems because of the expensiveness of interaction and limitation of budget at deployment. One aspect of the data inefficiency comes from the expensive hyper-parameter tuning when optimizing deep neural networks. We propose Adaptive Behavior Policy Sharing (ABPS), a data-efficient training algorithm that allows sharing of experience collected by behavior policy that is ad"},"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":"2002.05229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T20:35:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0930f2dfeed566c27f6eb9fc94cd2bb90c28806bc241d101cef2925b1feb3606","abstract_canon_sha256":"ca5f555864821cc7182eb49f877d1fc5e2b4a4b74b9b0659c9ddd9ae13d6b95c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:29.290628Z","signature_b64":"jMkkWYebsOp3Z29/6zpdPC7sOAhSzw88LHtZEJbr8ZnZs+pFqjYNK8OpduCC6JMLN/yzF2O+jtGsAVXNz60MCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7907e50a2198571548b6be460bf0eebebed930e553419edfbdfa6c864b652f10","last_reissued_at":"2026-07-05T00:40:29.290171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:29.290171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Efficient Training for Reinforcement Learning with Adaptive Behavior Policy Sharing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ang Li, Craig Boutilier, Ed Chi, Ge Liu, Heng-Tze Cheng, Jayden Ooi, Jing Wang, Lihong Li, Rui Wu, Wai Lok Sibon Li","submitted_at":"2020-02-12T20:35:31Z","abstract_excerpt":"Deep Reinforcement Learning (RL) is proven powerful for decision making in simulated environments. However, training deep RL model is challenging in real world applications such as production-scale health-care or recommender systems because of the expensiveness of interaction and limitation of budget at deployment. One aspect of the data inefficiency comes from the expensive hyper-parameter tuning when optimizing deep neural networks. We propose Adaptive Behavior Policy Sharing (ABPS), a data-efficient training algorithm that allows sharing of experience collected by behavior policy that is ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05229","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/2002.05229/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":"2002.05229","created_at":"2026-07-05T00:40:29.290241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05229v1","created_at":"2026-07-05T00:40:29.290241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05229","created_at":"2026-07-05T00:40:29.290241+00:00"},{"alias_kind":"pith_short_12","alias_value":"PED6KCRBTBLR","created_at":"2026-07-05T00:40:29.290241+00:00"},{"alias_kind":"pith_short_16","alias_value":"PED6KCRBTBLRKSFW","created_at":"2026-07-05T00:40:29.290241+00:00"},{"alias_kind":"pith_short_8","alias_value":"PED6KCRB","created_at":"2026-07-05T00:40:29.290241+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/PED6KCRBTBLRKSFWXZDAX4HOX2","json":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2.json","graph_json":"https://pith.science/api/pith-number/PED6KCRBTBLRKSFWXZDAX4HOX2/graph.json","events_json":"https://pith.science/api/pith-number/PED6KCRBTBLRKSFWXZDAX4HOX2/events.json","paper":"https://pith.science/paper/PED6KCRB"},"agent_actions":{"view_html":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2","download_json":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2.json","view_paper":"https://pith.science/paper/PED6KCRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05229&json=true","fetch_graph":"https://pith.science/api/pith-number/PED6KCRBTBLRKSFWXZDAX4HOX2/graph.json","fetch_events":"https://pith.science/api/pith-number/PED6KCRBTBLRKSFWXZDAX4HOX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2/action/storage_attestation","attest_author":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2/action/author_attestation","sign_citation":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2/action/citation_signature","submit_replication":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2/action/replication_record"}},"created_at":"2026-07-05T00:40:29.290241+00:00","updated_at":"2026-07-05T00:40:29.290241+00:00"}