{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_a9f60aaa00748b57e0e59729378048b7854b521129f0a80f4533416ad9a2e4d0","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_a9f60aaa00748b57e0e59729378048b7854b521129f0a80f4533416ad9a2e4d0","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"20b9f9179feca94ac3bb6a1d497b16b32a54f01df078b9d567226e9d05347b44","published":"Fri, 15 May 2026 00:00:00 -0400","receipt_hash":"20b9f9179feca94ac3bb6a1d497b16b32a54f01df078b9d567226e9d05347b44","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"20b9f9179feca94ac3bb6a1d497b16b32a54f01df078b9d567226e9d05347b44","observed_at":"2026-05-15T04:43:17.611638Z","parent_run_hash":"5c64f85625fabd323e9c4a1cf068c012fb88a248deda9a9ac702fb2f9799f2e5","published":"Fri, 15 May 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2602.07441v2 Announce Type: replace-cross \nAbstract: 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 already dominant. We formally analyzed this limitation by investigating convergence properties of BC-regularized actor-critic optimization and verified it on a controlled continuous bandit task. To break this ceiling, we propose proximal action replacement (PAR), an easy-to-use plug-and-play training sample replacer. PAR substitutes subopti","title":"Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning","url":"https://arxiv.org/abs/2602.07441","vendor":"arxiv_cs_ai"},"summary":"arXiv:2602.07441v2 Announce Type: replace-cross \nAbstract: 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 already dominant. We formally analyzed this limitation by investigating convergence properties of BC-regularized actor-critic optimization and verified it on a controlled continuous bandit task. To break this ceiling, we propose proximal action replacement (PAR), an easy-to-use plug-and-play training sample replacer. PAR substitutes subopti","title":"Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-15T04:43:17Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2602.07441"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:afc0feefa88287210497fa65b4cf18ec26209d7cdb46b89e1b7311e090cf5c4311323a678b822ee926b832352678a0bb63b066978f7aa0737f6e14b12a5dd20f","signer":"crovia.substrate","subject":{"observed_at":"2026-05-15T04:43:17Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2602.07441"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"eb3d1450e40cdff3f11247c856ed63a47dc876188a0189d0b6bfe617d56e80ee","leaf_index":134767,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"254d35a0a01066bc3c1f919cdcbeba4f9c1e330e9618915fd79941182bd7a71e","side":"left"},{"sibling":"68d66a97ad93b591de91d000e541d8a9a6215205142683b5bf1cd3f11badac3f","side":"left"},{"sibling":"a227dd46da69a4487a52dbfbda6a5e95a93ca4a3b3105d13ea31f6446d6b342d","side":"left"},{"sibling":"f8d54f25c5c6a3899698f1b719457c48a0191fc6d08ac6c40f72e617359b8ffd","side":"left"},{"sibling":"37ba49eedf02189e9205dda7034b06c5dea5c0b014937cfd3d4b16e4d6725e50","side":"right"},{"sibling":"952bb2ea9b8e1bb4f01c53d0e4d6522140e49683ac624344442d5a1522d7c3be","side":"left"},{"sibling":"4999a953ceed25471a2bccd6eadce4cee20773995bf2d506b76320a8705da9a4","side":"left"},{"sibling":"d8ac22bfe982d5dc7f00879b0b1dfae8f4e95a38a6242933cbebb3b7271d5704","side":"right"},{"sibling":"a17a0eaa87574a308e2c02cf125072b9e69566b9e8d6d2e64a02880192b885d5","side":"right"},{"sibling":"6bd0475fd3a73322a4f73095c96b072de89e462ce5839161aa552e0208619bce","side":"left"},{"sibling":"36672459e5ed50c64ee1842b69cb6d2eb682c2a04844555be8d124257571994a","side":"left"},{"sibling":"727783827652adfa99c455bd80a01bfb33836228e51068b4f654ef3da468ca69","side":"left"},{"sibling":"623194cd30880ed223e306737fdb111aa0d781751bfc47553c404a6af6aad2c4","side":"right"},{"sibling":"fc8f53ed42756907fb79ee19a4ed09f72c560e5302b3d98198b96bf1da635a4a","side":"right"},{"sibling":"d6607539da7ba39ec68be2d12f27ed6768766c745e3120fd915f88c5e288e07c","side":"right"},{"sibling":"b63408a424d27cd6a75e0fb155e69a58a328f41e9cb9dba1eddef9a5289cc7fd","side":"right"},{"sibling":"356fb36a4e188f03d7a05c54cd8789bdd40eda454b9bc9560f667acc08e6c4e0","side":"right"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":134886,"merkle_root":"c6c7ae28c065bced89e7f844216b073f1a7cc4b378db0d41a98bcd21b28066db","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T05:37:26Z","sig_algorithm":"ed25519","signature":"5a3978c26017daf4104adbb3e1c3099c5750157acbfc7242ece1815dc6740fe08a690291ce0afe42011e20cc565b5ebe64ec016bf658b5bab563a63337985c05","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_a9f60aaa00748b57e0e59729378048b7854b521129f0a80f4533416ad9a2e4d0"}}