{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PED6KCRBTBLRKSFWXZDAX4HOX2","short_pith_number":"pith:PED6KCRB","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"},"canonical_sha256":"7907e50a2198571548b6be460bf0eebebed930e553419edfbdfa6c864b652f10","source":{"kind":"arxiv","id":"2002.05229","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.05229","created_at":"2026-07-05T00:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"2002.05229v1","created_at":"2026-07-05T00:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05229","created_at":"2026-07-05T00:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"PED6KCRBTBLR","created_at":"2026-07-05T00:40:29Z"},{"alias_kind":"pith_short_16","alias_value":"PED6KCRBTBLRKSFW","created_at":"2026-07-05T00:40:29Z"},{"alias_kind":"pith_short_8","alias_value":"PED6KCRB","created_at":"2026-07-05T00:40:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PED6KCRBTBLRKSFWXZDAX4HOX2","target":"record","payload":{"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"},"canonical_sha256":"7907e50a2198571548b6be460bf0eebebed930e553419edfbdfa6c864b652f10","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"},"source_kind":"arxiv","source_id":"2002.05229","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eBN8JvTeouryfhkO2qkMnyKZHSUHaGVT+3ZKjoXJ6TxhqDWs9/MIF5khFQaYl+9Iyi0TbdvQqEu4anwaQcJ5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T05:38:48.218492Z"},"content_sha256":"2d4b1e50263159bd4666bd30dbf002f9a7b5f908e46c8b28ae07fa1a2c2196e0","schema_version":"1.0","event_id":"sha256:2d4b1e50263159bd4666bd30dbf002f9a7b5f908e46c8b28ae07fa1a2c2196e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PED6KCRBTBLRKSFWXZDAX4HOX2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VxNmXL9yaU40EuejA7AXYWhMnb4QKGShm2SkSqesArsy55UQCQOinu5pMqfZgFXQuElpZ7xFGFvdGlNOHCg5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T05:38:48.218874Z"},"content_sha256":"22b82dd00fa22680c2d64f3a847248f3bcb1a1aaaecdd48a605ee40111ab7416","schema_version":"1.0","event_id":"sha256:22b82dd00fa22680c2d64f3a847248f3bcb1a1aaaecdd48a605ee40111ab7416"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2/bundle.json","state_url":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PED6KCRBTBLRKSFWXZDAX4HOX2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-05T05:38:48Z","links":{"resolver":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2","bundle":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2/bundle.json","state":"https://pith.science/pith/PED6KCRBTBLRKSFWXZDAX4HOX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PED6KCRBTBLRKSFWXZDAX4HOX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PED6KCRBTBLRKSFWXZDAX4HOX2","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":"ca5f555864821cc7182eb49f877d1fc5e2b4a4b74b9b0659c9ddd9ae13d6b95c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T20:35:31Z","title_canon_sha256":"0930f2dfeed566c27f6eb9fc94cd2bb90c28806bc241d101cef2925b1feb3606"},"schema_version":"1.0","source":{"id":"2002.05229","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.05229","created_at":"2026-07-05T00:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"2002.05229v1","created_at":"2026-07-05T00:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05229","created_at":"2026-07-05T00:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"PED6KCRBTBLR","created_at":"2026-07-05T00:40:29Z"},{"alias_kind":"pith_short_16","alias_value":"PED6KCRBTBLRKSFW","created_at":"2026-07-05T00:40:29Z"},{"alias_kind":"pith_short_8","alias_value":"PED6KCRB","created_at":"2026-07-05T00:40:29Z"}],"graph_snapshots":[{"event_id":"sha256:22b82dd00fa22680c2d64f3a847248f3bcb1a1aaaecdd48a605ee40111ab7416","target":"graph","created_at":"2026-07-05T00:40:29Z","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/2002.05229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T20:35:31Z","title":"Data Efficient Training for Reinforcement Learning with Adaptive Behavior Policy Sharing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05229","kind":"arxiv","version":1},"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":"sha256:2d4b1e50263159bd4666bd30dbf002f9a7b5f908e46c8b28ae07fa1a2c2196e0","target":"record","created_at":"2026-07-05T00:40:29Z","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":"ca5f555864821cc7182eb49f877d1fc5e2b4a4b74b9b0659c9ddd9ae13d6b95c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T20:35:31Z","title_canon_sha256":"0930f2dfeed566c27f6eb9fc94cd2bb90c28806bc241d101cef2925b1feb3606"},"schema_version":"1.0","source":{"id":"2002.05229","kind":"arxiv","version":1}},"canonical_sha256":"7907e50a2198571548b6be460bf0eebebed930e553419edfbdfa6c864b652f10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7907e50a2198571548b6be460bf0eebebed930e553419edfbdfa6c864b652f10","first_computed_at":"2026-07-05T00:40:29.290171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:29.290171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jMkkWYebsOp3Z29/6zpdPC7sOAhSzw88LHtZEJbr8ZnZs+pFqjYNK8OpduCC6JMLN/yzF2O+jtGsAVXNz60MCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:29.290628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.05229","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d4b1e50263159bd4666bd30dbf002f9a7b5f908e46c8b28ae07fa1a2c2196e0","sha256:22b82dd00fa22680c2d64f3a847248f3bcb1a1aaaecdd48a605ee40111ab7416"],"state_sha256":"219898208b8c4f23d4f40fbd49fcf1fc54379bcae455bce3111de706c4264755"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m4WuPMNkQRdP/NS0MCc9QFeGKGLEauckeuSM4ltG7pQ0ay2u/hFZ4BLC0M5xVPDAV9M5dTeOuOj3/CNdkBvLAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T05:38:48.221146Z","bundle_sha256":"095a00c69b3ee9c2a3b138a4f681479af2dd043d97c9980b8f6cb299f7fff4ab"}}