{"_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_f16f64a5b23d6eba55ce86cc83da39268a665e27a194903ca50b9f779e1efe14","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_f16f64a5b23d6eba55ce86cc83da39268a665e27a194903ca50b9f779e1efe14","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"b623de1b59def5c34e009b3679024e3269c2a6cba1d4a6bdbb6d8970387e6f92","published":"Mon, 20 Jul 2026 00:00:00 -0400","receipt_hash":"b623de1b59def5c34e009b3679024e3269c2a6cba1d4a6bdbb6d8970387e6f92","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":"b623de1b59def5c34e009b3679024e3269c2a6cba1d4a6bdbb6d8970387e6f92","observed_at":"2026-07-20T04:43:09.641409Z","parent_run_hash":"0fd83663f0f57da59b26313ca1a35283a3e9f06e3165d3e143d26f7174743aca","published":"Mon, 20 Jul 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:2606.30072v2 Announce Type: replace \nAbstract: Cooperative tasks in Multi-Agent Reinforcement Learning (MARL) require agents to collectively maximize a shared return. Under the Centralized Training with Decentralized Execution (CTDE) paradigm, policy gradients have remained difficult to compute directly. Prior methods largely follow two approaches: independent factorized updates with centralized critics, which lack general joint-improvement guarantees without value decomposition assumptions, or alternating best-response updates, which can converge to suboptimal Nash Equilibria. In this paper, we show the joint policy gradient admits an exact decentralized decomposition of per-agent terms, each formed from per-agent score functions and decentralized critics. Based on this decomposition, we develop Agent-Chained Policy Optimization (ACPO), where actors are trained independently, with their updates together constituting a single step on the joint policy gradient. Central to this res","title":"ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning","url":"https://arxiv.org/abs/2606.30072","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.30072v2 Announce Type: replace \nAbstract: Cooperative tasks in Multi-Agent Reinforcement Learning (MARL) require agents to collectively maximize a shared return. Under the Centralized Training with Decentralized Execution (CTDE) paradigm, policy gradients have remained difficult to compute directly. Prior methods largely follow two approaches: independent factorized updates with centralized critics, which lack general joint-improvement guarantees without value decomposition assumptions, or alternating best-response updates, which can converge to suboptimal Nash Equilibria. In this paper, we show the joint policy gradient admits an exact decentralized decomposition of per-agent terms, each formed from per-agent score functions and decentralized critics. Based on this decomposition, we develop Agent-Chained Policy Optimization (ACPO), where actors are trained independently, with their updates together constituting a single step on the joint policy gradient. Central to this res","title":"ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-20T04:43:09Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.30072"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:307691c0b57991783d122e94da94f323bed44f648b3ae706f88c349c859d3512c599c15d59c0370d88fe1f27ee89deb55cbde24bc3631c624d24d537bf2d3900","signer":"crovia.substrate","subject":{"observed_at":"2026-07-20T04:43:09Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.30072"},"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":"5ec41bc05b3f7f492119f91c222afb2b026f37aae8ba981e60c12091a17815f9","leaf_index":333345,"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":"c183e0e758ed3b75c3fda2469ed41dedfceaeebb89647ed4b2140874a1afab3d","side":"left"},{"sibling":"8cb3c26e2f382ef5466ed5100df8d8b870ee9b2cd9349e23a07d7dcdde8c36dd","side":"right"},{"sibling":"2899e9cc122d5bc984bee50911430b541ba9204537af69e471e44babc3721bb1","side":"right"},{"sibling":"e24375542eece1ee1b1f54083d81886404ef61c98aac75d202c9ca0c8bce67da","side":"right"},{"sibling":"7a7893cc8f38a5f9a49eedec199c3ec5e1a71385c85563ac0cea3cb31a258d29","side":"right"},{"sibling":"0d19791e9aa074b8130eeb2e01249774582a5873ad2fb1aeac0e5267891a9a37","side":"left"},{"sibling":"335e5d86a4ea00f87721afcb0e730f04bbef2c17cd5489f5b8263047ffc4ccd3","side":"right"},{"sibling":"5f23b1a0a67d8fa1aa690680510620f249f8d6683d46c202fca306510fbe398e","side":"right"},{"sibling":"f720760992870795e6d2b913ad9162f9e144b821ea97e4dada744d0cac06e93b","side":"right"},{"sibling":"45c0e4431502711514503abd48e8b3d34ee2f4bffa994c883aaf2adecd0ad8e9","side":"left"},{"sibling":"dedd2da92d9447ddf1b1db68fe20109a426ed18359861ed746907ac820021a8d","side":"left"},{"sibling":"a1c43cc7cd9c775fac33940ee5124aece01596733f003fc53743f43483f9f597","side":"right"},{"sibling":"b5ad3eafd7eeb74c063261356fdd9bf6059ee6d0bf1e3c70e60731b394a5536e","side":"left"},{"sibling":"93e399d152203db688c6a5a58d25131205603504f5b79123a1f2b5a5ed9c1e54","side":"right"},{"sibling":"b6e0cad7f6eb9107f0edd276f1a9942635d8cd6d60d2a97e7daac08b110dc209","side":"right"},{"sibling":"80ec062e7e625dc3f9bb5865cb5198696bbec2608e48abae5670677b90695899","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"0aced6f0c9dec3e6cc9e89b68b70f5f8ce7e1eb13606d92db1917b76e57393c7","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":333540,"merkle_root":"ee60f62b8a724dd9bde638d638caf32cefec4440f832018b457ff47a0ec56a8c","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260720T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-20T05:38:36Z","sig_algorithm":"ed25519","signature":"82a3787e628bfab19c377d875220e1aaedfc498736c545f4708a1b887e8398afdf306995994493a36c864ff7139a2d436b905ce7081aaa540789aa4f707dc800","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_f16f64a5b23d6eba55ce86cc83da39268a665e27a194903ca50b9f779e1efe14"}}