{"_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_a986e3412b608d13362a517d95af37a06f2f10e7ed9c592c6cfca76a28b6f1ef","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_a986e3412b608d13362a517d95af37a06f2f10e7ed9c592c6cfca76a28b6f1ef","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"79defcebe1259151e6f23997e73740e54e4ed0d2b417db2aa462712bb64eea9e","published":"Fri, 15 May 2026 00:00:00 -0400","receipt_hash":"79defcebe1259151e6f23997e73740e54e4ed0d2b417db2aa462712bb64eea9e","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":"79defcebe1259151e6f23997e73740e54e4ed0d2b417db2aa462712bb64eea9e","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:2605.14379v1 Announce Type: cross \nAbstract: Finding approximate equilibria for large-scale imperfect-information competitive games such as StarCraft, Dota, and CounterStrike remains computationally infeasible due to sparse rewards and challenging exploration over long horizons. In this paper, we propose a multi-agent starting-state sampling strategy designed to substantially accelerate online exploration in regularized policy-gradient game methods for two-player zero-sum (2p0s) games. Motivated by an assumption that offline demonstrations from skilled humans can provide good coverage of high-level strategies relevant to equilibrium play, we propose the initialization of reinforcement learning data collection at intermediate states sampled from offline data to facilitate exploration of strategically relevant subgames. Referring to this method as Data-Augmented Game Starts (DAGS), we perform experiments using synthetic datasets and analytically tractable, long-horizon control vari","title":"Data-Augmented Game Starts for Accelerating Self-Play Exploration in Imperfect Information Games","url":"https://arxiv.org/abs/2605.14379","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.14379v1 Announce Type: cross \nAbstract: Finding approximate equilibria for large-scale imperfect-information competitive games such as StarCraft, Dota, and CounterStrike remains computationally infeasible due to sparse rewards and challenging exploration over long horizons. In this paper, we propose a multi-agent starting-state sampling strategy designed to substantially accelerate online exploration in regularized policy-gradient game methods for two-player zero-sum (2p0s) games. Motivated by an assumption that offline demonstrations from skilled humans can provide good coverage of high-level strategies relevant to equilibrium play, we propose the initialization of reinforcement learning data collection at intermediate states sampled from offline data to facilitate exploration of strategically relevant subgames. Referring to this method as Data-Augmented Game Starts (DAGS), we perform experiments using synthetic datasets and analytically tractable, long-horizon control vari","title":"Data-Augmented Game Starts for Accelerating Self-Play Exploration in Imperfect Information Games","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/2605.14379"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:f90e39eb59d4ff49dc3e5751f9c713732a512abb0517b32b9589fb13a128c9bb1c56a17a717999b263bbdeea0a2373f297d56f87c2e3ae36b6a400ec8a74c001","signer":"crovia.substrate","subject":{"observed_at":"2026-05-15T04:43:17Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.14379"},"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":"c3a70a838fcd5651eb90fe8da245117ab0783bd14af6344d679fca26e06f6844","leaf_index":134571,"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":"a65976eb0d92c7476283435660c2f43f0950d8d304d21081ae35f183d86ba0aa","side":"left"},{"sibling":"b348e97a8a64cab7edf98ea1e8e1b0eac8c9d472870cc4f11e18700ffdce0fb1","side":"left"},{"sibling":"05c8d16fac882c182207bb57ad7661e3a9af53f18a3be8eccc1b891fb5a6ee19","side":"right"},{"sibling":"524d554e95200436a3fbf0afa7e377001e7f1cc03ba09e0a73dba533410fac3c","side":"left"},{"sibling":"7a281393c8917ff58e8886b5a48a1f56219aba98c63c2d3b80b9dcd942f66e8f","side":"right"},{"sibling":"43982a5bd6cb35267ed601264f34987c93cb2862634ff99b69b128e231583d53","side":"left"},{"sibling":"1fcc844afba4d276ea40006549a4217e03b90b0c4aa39feb95e5883e34363df9","side":"right"},{"sibling":"cbbed0225164fe227925f0fc2929e9ecbc520f5a86b19035c412206d51935e10","side":"left"},{"sibling":"4711a7f4329f1874c3aa1ae93c336e1d4fa402bdd4b3d766c2a95304ea226882","side":"left"},{"sibling":"8ce2a4687a8ceb409df2e1cb10e44a610b21dc294e518a8550b6d1122335ca2b","side":"right"},{"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_a986e3412b608d13362a517d95af37a06f2f10e7ed9c592c6cfca76a28b6f1ef"}}