{"_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_b3ec8091bcd28197610ed34eab5e198ea3a2fb2deecb49c880b33107a823264a","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_b3ec8091bcd28197610ed34eab5e198ea3a2fb2deecb49c880b33107a823264a","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"7f76a803f38885e114cdec15ece5df0f70f39f2b00c02b598afc9f9278216bb3","published":"Wed, 10 Jun 2026 00:00:00 -0400","receipt_hash":"7f76a803f38885e114cdec15ece5df0f70f39f2b00c02b598afc9f9278216bb3","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":"7f76a803f38885e114cdec15ece5df0f70f39f2b00c02b598afc9f9278216bb3","observed_at":"2026-06-10T04:43:37.461885Z","parent_run_hash":"23aff1a6f676ba7ca33f70f4ddfae1dd282fb86104d577ce9be510d81a94c5dc","published":"Wed, 10 Jun 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:2606.10835v1 Announce Type: cross \nAbstract: Periodic hard target updates are among the most common stabilization devices in modern deep Q-learning. Recent studies suggest that target updates can improve stability in Q-learning with function approximation, including linear function approximation. We introduce and analyze the so-called $\\lambda$-target update, obtained by averaging the $m$-periodic target update maps with $\\lambda$-geometric weights $(1-\\lambda)\\lambda^{m-1}$, $\\lambda \\in [0,1]$. The endpoint $\\lambda=0$ recovers the one-period target update, while the continuous endpoint $\\lambda\\uparrow1$ recovers projected Q-value iteration. We study this mechanism for Q-learning with linear function approximation, namely linear Q-learning, using a switching-system model and related tools. For clarity, the paper treats a deterministic version; the formulation extends to stochastic reinforcement-learning settings.","title":"Geometrically Averaged Hard Target Updates for Linear Q-Learning","url":"https://arxiv.org/abs/2606.10835","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.10835v1 Announce Type: cross \nAbstract: Periodic hard target updates are among the most common stabilization devices in modern deep Q-learning. Recent studies suggest that target updates can improve stability in Q-learning with function approximation, including linear function approximation. We introduce and analyze the so-called $\\lambda$-target update, obtained by averaging the $m$-periodic target update maps with $\\lambda$-geometric weights $(1-\\lambda)\\lambda^{m-1}$, $\\lambda \\in [0,1]$. The endpoint $\\lambda=0$ recovers the one-period target update, while the continuous endpoint $\\lambda\\uparrow1$ recovers projected Q-value iteration. We study this mechanism for Q-learning with linear function approximation, namely linear Q-learning, using a switching-system model and related tools. For clarity, the paper treats a deterministic version; the formulation extends to stochastic reinforcement-learning settings.","title":"Geometrically Averaged Hard Target Updates for Linear Q-Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-10T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.10835"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:8ed63595ee8f6e6501853e19f32a58965e56c24ed03a91acc9041f6c778d3ad9e013fbc9b2127899daee9c7db94ad6d0f63bf7b95ffbd9435b0dee64ef725c04","signer":"crovia.substrate","subject":{"observed_at":"2026-06-10T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.10835"},"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":"66e4a6aff3d3bee69211043d0fbe25889740f76158eefb27385cad4ab0abe498","leaf_index":226086,"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":"da5a5604c4695635fd2c6f74e0d8259f8b943573d2fae5f8829c88c37f20561e","side":"right"},{"sibling":"7c02efeaf35f801c05c534dc914024da990cb50d5ebc4325992ea4bc520b62ab","side":"left"},{"sibling":"db9b2117b249ddd17b59bc04bfe87ac8764fbdadcd8a595ff204ca56f1fe7708","side":"left"},{"sibling":"67ea6fc648beed084486519a48f2164e8a0e67ac639ea8443313743affb25878","side":"right"},{"sibling":"76b9c0731b3879456d5b8be5032f2e3a74c3c41f361be288cb21b2691b65bd97","side":"right"},{"sibling":"c45d6316d9967be11fb5ebc30788b1e275d0bcba0f31abb481c71675b76a224d","side":"left"},{"sibling":"88b2be21cb27d1f77926cea4c04fb2bafb96cdf167c1655dc8560cea37cb31bf","side":"right"},{"sibling":"670eed753a274b9b7494adeace1b88e7adfaecd7eeaa78b82e0fc83a75d20865","side":"right"},{"sibling":"b180cfc3f8638c912e90139ec42e2e3fd9b67b3fe342b36e8954314633ae5f61","side":"left"},{"sibling":"a4d17aefe58175050dc159af6246658fcf1c9f3ed57aacf1b350fc3261de4e69","side":"left"},{"sibling":"280b980aa0c7756b0b0cb22658f26466d36f0e70fbc3312cd2311d9898e30b8f","side":"right"},{"sibling":"c98954d4b658b1dda60fe52576fcf9bf21a2d49c67fb63f8c30f16ab5f721938","side":"right"},{"sibling":"cdb58f86163046d3b15f857b03372ec75e1ad9ea4548e086793d528b9eed364d","side":"left"},{"sibling":"533d82482604463aa4a281b9d8b85917b383b7c5f924b2b494039524c55e8797","side":"left"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"6cea4964f32722eb370847c2f7c9d6a9f0622c239538b07e6815a59d6fd8d49c","side":"right"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"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":228173,"merkle_root":"7e416202c0bfd759bd2eea4236713b403993d99793fe8badb5065040080bece3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260611T143708Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-11T21:59:35Z","sig_algorithm":"ed25519","signature":"231c80024bc3982dd493c45b31af95097e97aabc6d712a4e5bad7d0cbdd3c08e01ff395b0f8e72754bac97016e0cd0eed88b8a13cb71edbbcb9b6d72c10a7b03","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_b3ec8091bcd28197610ed34eab5e198ea3a2fb2deecb49c880b33107a823264a"}}