{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:V32KOQDVHYV57NJEBZ5RZD6ERP","short_pith_number":"pith:V32KOQDV","canonical_record":{"source":{"id":"2405.18520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T18:38:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4cfb0e9205ed3a7bb0a9a0afa96e3f88dd9218962b4b3f8e8cf4e395f206ec96","abstract_canon_sha256":"3a578ec4414714c61f99e0d840138d328571cb2ffc09adf724252bae1e1f23b5"},"schema_version":"1.0"},"canonical_sha256":"aef4a740753e2bdfb5240e7b1c8fc48bfee21ae60ba78a8d1c74da9ac9d7019a","source":{"kind":"arxiv","id":"2405.18520","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18520","created_at":"2026-07-05T08:24:26Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18520v1","created_at":"2026-07-05T08:24:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18520","created_at":"2026-07-05T08:24:26Z"},{"alias_kind":"pith_short_12","alias_value":"V32KOQDVHYV5","created_at":"2026-07-05T08:24:26Z"},{"alias_kind":"pith_short_16","alias_value":"V32KOQDVHYV57NJE","created_at":"2026-07-05T08:24:26Z"},{"alias_kind":"pith_short_8","alias_value":"V32KOQDV","created_at":"2026-07-05T08:24:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:V32KOQDVHYV57NJEBZ5RZD6ERP","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T18:38:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4cfb0e9205ed3a7bb0a9a0afa96e3f88dd9218962b4b3f8e8cf4e395f206ec96","abstract_canon_sha256":"3a578ec4414714c61f99e0d840138d328571cb2ffc09adf724252bae1e1f23b5"},"schema_version":"1.0"},"canonical_sha256":"aef4a740753e2bdfb5240e7b1c8fc48bfee21ae60ba78a8d1c74da9ac9d7019a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:26.466552Z","signature_b64":"7i/RtJFgeBgWn+sOoUOC62oxinbsa8dRT19E5RqY9LS4B/66Dvo3+h4iisqQ8VNJXXhQh6B4k3xX17iQqcTWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aef4a740753e2bdfb5240e7b1c8fc48bfee21ae60ba78a8d1c74da9ac9d7019a","last_reissued_at":"2026-07-05T08:24:26.466169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:26.466169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18520","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":"2026-07-05T08:24:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+NpJguAz7x0smCPTerhExa1oc+lH7ddPeXskDqtFIT8vdfLfCXIayYZLrVPOlR9VSJB+qcC4w9H5Opz+lVHwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:13:59.406652Z"},"content_sha256":"40fdd1883d0d61879d68fcb40c5d9621b785a77818e589cd10b742b68646f651","schema_version":"1.0","event_id":"sha256:40fdd1883d0d61879d68fcb40c5d9621b785a77818e589cd10b742b68646f651"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:V32KOQDVHYV57NJEBZ5RZD6ERP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fuchun Sun, Huazhe Xu, Jianwei Zhang, Tianying Ji, Xianyuan Zhan, Yu Luo","submitted_at":"2024-05-28T18:38:46Z","abstract_excerpt":"Off-policy reinforcement learning (RL) has achieved notable success in tackling many complex real-world tasks, by leveraging previously collected data for policy learning. However, most existing off-policy RL algorithms fail to maximally exploit the information in the replay buffer, limiting sample efficiency and policy performance. In this work, we discover that concurrently training an offline RL policy based on the shared online replay buffer can sometimes outperform the original online learning policy, though the occurrence of such performance gains remains uncertain. This motivates a new "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18520","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/2405.18520/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":"2026-07-05T08:24:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0J/51jbu1E8HgJe8JtaUpUe9Z3paL9JWMu/kbzc8VOyZ1W8SCscTD3c4yIuNOwAAi76wCG6Xha4gCU9wkvtXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:13:59.407157Z"},"content_sha256":"47e07261eb3865e794f8d3c7272bec7c19f0959fd52f5e177e59f69f9484f3d9","schema_version":"1.0","event_id":"sha256:47e07261eb3865e794f8d3c7272bec7c19f0959fd52f5e177e59f69f9484f3d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V32KOQDVHYV57NJEBZ5RZD6ERP/bundle.json","state_url":"https://pith.science/pith/V32KOQDVHYV57NJEBZ5RZD6ERP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V32KOQDVHYV57NJEBZ5RZD6ERP/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":"2026-08-03T16:13:59Z","links":{"resolver":"https://pith.science/pith/V32KOQDVHYV57NJEBZ5RZD6ERP","bundle":"https://pith.science/pith/V32KOQDVHYV57NJEBZ5RZD6ERP/bundle.json","state":"https://pith.science/pith/V32KOQDVHYV57NJEBZ5RZD6ERP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V32KOQDVHYV57NJEBZ5RZD6ERP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V32KOQDVHYV57NJEBZ5RZD6ERP","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":"3a578ec4414714c61f99e0d840138d328571cb2ffc09adf724252bae1e1f23b5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T18:38:46Z","title_canon_sha256":"4cfb0e9205ed3a7bb0a9a0afa96e3f88dd9218962b4b3f8e8cf4e395f206ec96"},"schema_version":"1.0","source":{"id":"2405.18520","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18520","created_at":"2026-07-05T08:24:26Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18520v1","created_at":"2026-07-05T08:24:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18520","created_at":"2026-07-05T08:24:26Z"},{"alias_kind":"pith_short_12","alias_value":"V32KOQDVHYV5","created_at":"2026-07-05T08:24:26Z"},{"alias_kind":"pith_short_16","alias_value":"V32KOQDVHYV57NJE","created_at":"2026-07-05T08:24:26Z"},{"alias_kind":"pith_short_8","alias_value":"V32KOQDV","created_at":"2026-07-05T08:24:26Z"}],"graph_snapshots":[{"event_id":"sha256:47e07261eb3865e794f8d3c7272bec7c19f0959fd52f5e177e59f69f9484f3d9","target":"graph","created_at":"2026-07-05T08:24:26Z","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/2405.18520/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy reinforcement learning (RL) has achieved notable success in tackling many complex real-world tasks, by leveraging previously collected data for policy learning. However, most existing off-policy RL algorithms fail to maximally exploit the information in the replay buffer, limiting sample efficiency and policy performance. In this work, we discover that concurrently training an offline RL policy based on the shared online replay buffer can sometimes outperform the original online learning policy, though the occurrence of such performance gains remains uncertain. This motivates a new ","authors_text":"Fuchun Sun, Huazhe Xu, Jianwei Zhang, Tianying Ji, Xianyuan Zhan, Yu Luo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T18:38:46Z","title":"Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18520","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":"sha256:40fdd1883d0d61879d68fcb40c5d9621b785a77818e589cd10b742b68646f651","target":"record","created_at":"2026-07-05T08:24:26Z","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":"3a578ec4414714c61f99e0d840138d328571cb2ffc09adf724252bae1e1f23b5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T18:38:46Z","title_canon_sha256":"4cfb0e9205ed3a7bb0a9a0afa96e3f88dd9218962b4b3f8e8cf4e395f206ec96"},"schema_version":"1.0","source":{"id":"2405.18520","kind":"arxiv","version":1}},"canonical_sha256":"aef4a740753e2bdfb5240e7b1c8fc48bfee21ae60ba78a8d1c74da9ac9d7019a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aef4a740753e2bdfb5240e7b1c8fc48bfee21ae60ba78a8d1c74da9ac9d7019a","first_computed_at":"2026-07-05T08:24:26.466169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:26.466169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7i/RtJFgeBgWn+sOoUOC62oxinbsa8dRT19E5RqY9LS4B/66Dvo3+h4iisqQ8VNJXXhQh6B4k3xX17iQqcTWDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:26.466552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18520","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40fdd1883d0d61879d68fcb40c5d9621b785a77818e589cd10b742b68646f651","sha256:47e07261eb3865e794f8d3c7272bec7c19f0959fd52f5e177e59f69f9484f3d9"],"state_sha256":"1ce573d068b1d9a4f1f7e4ee691c1e6115c26e03edae71aabe629ba619a8c9a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jUzZwej/QhpgUSyJGgRcO0pCqtTFCyaE7zhgmfxJinvxHYZby28tb+nPRLspg8tt3m6njYQsQTQhN7UHObHXCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:13:59.412013Z","bundle_sha256":"9a9ebeefe3f4587b2e15d1981fc0fa8b0dc75604e5320e6906f756443389221b"}}