{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LLYFYPQ7KKAXCZ5CC5ET4AMJQ5","short_pith_number":"pith:LLYFYPQ7","schema_version":"1.0","canonical_sha256":"5af05c3e1f52817167a217493e018987643dfe7037bdd563807d036431926018","source":{"kind":"arxiv","id":"2602.07441","version":2},"attestation_state":"computed","paper":{"title":"Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Proximal action replacement overcomes the imitation ceiling in BC-regularized actor-critic by substituting suboptimal dataset actions with value-guided improvements.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jianshu Zhang, Jinzong Dong, Nanyang Ye, Qinying Gu, Wei Huang, Xinzhe Yuan, Zhaohui Jiang, Zhuo Chen","submitted_at":"2026-02-07T08:44:27Z","abstract_excerpt":"Offline reinforcement learning (RL), which optimizes policies using a previously collected static dataset, is an important branch of RL. A popular and promising approach is to regularize actor-critic methods with behavior cloning (BC), which quickly yields realistic policies and mitigates bias from out-of-distribution actions, but it can impose an often-overlooked performance ceiling: when dataset actions are suboptimal, indiscriminate imitation structurally prevents the actor from fully exploiting better actions suggested by the value function, especially in later training when imitation is a"},"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":true},"canonical_record":{"source":{"id":"2602.07441","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-07T08:44:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"11ceda1decf65b89cb4513c31144ecd8ad1132fdbf83a6e4a8002b631649229e","abstract_canon_sha256":"dd379b69b869ef4149d7ec98a96f6edfb06f271348c99998106e1a120b549e75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:00.026965Z","signature_b64":"Vg+Kd9qWxY32oyaRVXD2CfocUR6iYqKTWKhJzoO7U0tG+AFOgbIt7DaiX5C2mkfpZ2VjA1rv3/L+GscDf6sLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5af05c3e1f52817167a217493e018987643dfe7037bdd563807d036431926018","last_reissued_at":"2026-05-17T23:39:00.026294Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:00.026294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Proximal action replacement overcomes the imitation ceiling in BC-regularized actor-critic by substituting suboptimal dataset actions with value-guided improvements.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jianshu Zhang, Jinzong Dong, Nanyang Ye, Qinying Gu, Wei Huang, Xinzhe Yuan, Zhaohui Jiang, Zhuo Chen","submitted_at":"2026-02-07T08:44:27Z","abstract_excerpt":"Offline reinforcement learning (RL), which optimizes policies using a previously collected static dataset, is an important branch of RL. A popular and promising approach is to regularize actor-critic methods with behavior cloning (BC), which quickly yields realistic policies and mitigates bias from out-of-distribution actions, but it can impose an often-overlooked performance ceiling: when dataset actions are suboptimal, indiscriminate imitation structurally prevents the actor from fully exploiting better actions suggested by the value function, especially in later training when imitation is a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PAR consistently improves performance across offline RL benchmarks and approaches state-of-the-art results simply by being combined with the basic TD3+BC.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That actions generated by the stable target policy, guided by local ascent of the action-value function and bounded by value uncertainty, can be substituted without destabilizing training or introducing new bias when dataset actions are suboptimal.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Proximal action replacement breaks the imitation ceiling in BC-regularized offline RL actor-critic by substituting suboptimal dataset actions with value-guided improvements from a stable target policy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Proximal action replacement overcomes the imitation ceiling in BC-regularized actor-critic by substituting suboptimal dataset actions with value-guided improvements.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1bc0a1fabe3a824f2cbee31b02a28a8816be6ac66e3e322e509f4b137528e168"},"source":{"id":"2602.07441","kind":"arxiv","version":2},"verdict":{"id":"6c7949de-5314-4c6a-a646-019cf8846fd1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T06:35:10.381452Z","strongest_claim":"PAR consistently improves performance across offline RL benchmarks and approaches state-of-the-art results simply by being combined with the basic TD3+BC.","one_line_summary":"Proximal action replacement breaks the imitation ceiling in BC-regularized offline RL actor-critic by substituting suboptimal dataset actions with value-guided improvements from a stable target policy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That actions generated by the stable target policy, guided by local ascent of the action-value function and bounded by value uncertainty, can be substituted without destabilizing training or introducing new bias when dataset actions are suboptimal.","pith_extraction_headline":"Proximal action replacement overcomes the imitation ceiling in BC-regularized actor-critic by substituting suboptimal dataset actions with value-guided improvements."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b3849650427f66a860cf10c7b6fc96a1e819ae0ca1a3067c74188460cb719665"},"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":"2602.07441","created_at":"2026-05-17T23:39:00.026435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.07441v2","created_at":"2026-05-17T23:39:00.026435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07441","created_at":"2026-05-17T23:39:00.026435+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLYFYPQ7KKAX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLYFYPQ7KKAXCZ5C","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLYFYPQ7","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.03075","citing_title":"Refining Compositional Diffusion for Reliable Long-Horizon Planning","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5","json":"https://pith.science/pith/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5.json","graph_json":"https://pith.science/api/pith-number/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5/graph.json","events_json":"https://pith.science/api/pith-number/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5/events.json","paper":"https://pith.science/paper/LLYFYPQ7"},"agent_actions":{"view_html":"https://pith.science/pith/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5","download_json":"https://pith.science/pith/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5.json","view_paper":"https://pith.science/paper/LLYFYPQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.07441&json=true","fetch_graph":"https://pith.science/api/pith-number/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5/action/storage_attestation","attest_author":"https://pith.science/pith/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5/action/author_attestation","sign_citation":"https://pith.science/pith/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5/action/citation_signature","submit_replication":"https://pith.science/pith/LLYFYPQ7KKAXCZ5CC5ET4AMJQ5/action/replication_record"}},"created_at":"2026-05-17T23:39:00.026435+00:00","updated_at":"2026-05-17T23:39:00.026435+00:00"}