{"_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_4dcb868bcd9be8646ead6cb9fd999b7d02dad379acebf3fe837c12759efa1e01","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_4dcb868bcd9be8646ead6cb9fd999b7d02dad379acebf3fe837c12759efa1e01","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"0759943164c0133de96bcc9a3e125435821ed56d661c7ff37c42adb1fbb99fe5","published":"Mon, 25 May 2026 00:00:00 -0400","receipt_hash":"0759943164c0133de96bcc9a3e125435821ed56d661c7ff37c42adb1fbb99fe5","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":"0759943164c0133de96bcc9a3e125435821ed56d661c7ff37c42adb1fbb99fe5","observed_at":"2026-05-25T04:43:48.841018Z","parent_run_hash":"56713422f06ad87427cd8cdcdb1ed341feb016b33c37198d9b168328d1df15fb","published":"Mon, 25 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:2605.23562v1 Announce Type: cross \nAbstract: Sparse rewards are a major bottleneck in multi-agent reinforcement learning (MARL), where simultaneous learning induces non-stationarity and makes reward design especially delicate. Reward shaping can accelerate learning, but in the multi-agent setting it must preserve the strategic structure of the problem rather than merely improve short-term optimization. We propose Automatic Reward-shaping in Multi-agent Systems (ARMS), a self-supervised reward shaping framework for MARL that learns dense shaping signals from sparse environmental rewards through trajectory ranking. Since single-agent trajectory-ranking guarantees do not directly transfer to MARL, we reformulate policy invariance through conditional best-response reasoning, and show that if certain conditions hold, then using shaping rewards preserves each agent's best-response set under fixed opponent policies, and consequently preserve the set of Nash equilibria. Guided by this pe","title":"ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning","url":"https://arxiv.org/abs/2605.23562","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.23562v1 Announce Type: cross \nAbstract: Sparse rewards are a major bottleneck in multi-agent reinforcement learning (MARL), where simultaneous learning induces non-stationarity and makes reward design especially delicate. Reward shaping can accelerate learning, but in the multi-agent setting it must preserve the strategic structure of the problem rather than merely improve short-term optimization. We propose Automatic Reward-shaping in Multi-agent Systems (ARMS), a self-supervised reward shaping framework for MARL that learns dense shaping signals from sparse environmental rewards through trajectory ranking. Since single-agent trajectory-ranking guarantees do not directly transfer to MARL, we reformulate policy invariance through conditional best-response reasoning, and show that if certain conditions hold, then using shaping rewards preserves each agent's best-response set under fixed opponent policies, and consequently preserve the set of Nash equilibria. Guided by this pe","title":"ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-25T04:43:48Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.23562"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:b59ab80440acc9c83014a562990af625fe8b8cb3749d6758426481ca12b01813235fdbd902034ea6ca0a98437dc38e139c3158d73689b132ed8ee8229d467203","signer":"crovia.substrate","subject":{"observed_at":"2026-05-25T04:43:48Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.23562"},"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":"1434c38e3c9f2a4c4c57deff2adca48e6520d88ad035d30c15da4c17cffb7086","leaf_index":149636,"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":"067756a675217f952a86df05e1e912e2390ebde7d305e02605d745fe7e6b2068","side":"right"},{"sibling":"3ad6f92fb6c17c357d92bbd699573ee32d4b48446b79d6f1e287cab95a20c1a4","side":"right"},{"sibling":"38b73282cc07fd412a7b6a06ad3d8e56a2ef91ecd9731a270d6223a9f17f9085","side":"left"},{"sibling":"c2ebec8e6c30f15e5216195a3d944d55626a8b0bba9ce2f77f4c455defe08655","side":"right"},{"sibling":"b887423e9ec646b26f77fd3c1d7ebfb950af1b730936f447874e71a25fa38577","side":"right"},{"sibling":"f61fe7709668d9c426e63af2ee198fb571873853484d18d2a5397d0eba756cc2","side":"right"},{"sibling":"919f4560dbaa8584ff90fc1ba33dc74b59dff462d40837f8f3cbb7a4f3d2f375","side":"right"},{"sibling":"cb71a04113e54ec457f452a34b2778696e1747afe98ba9da255ce1f5fd8619d7","side":"left"},{"sibling":"e044acc52c31efe134c902c984299ea3452b42df993d096ed61ad8be9d530bbc","side":"right"},{"sibling":"6be461ecf12dedf98a31921aa7b5c32d4a32df6897e0f697b8bf1a4ba3e2d324","side":"right"},{"sibling":"c2861a8cef3eb66bf2726aa377c24a6bf6e8b7489dcd0e870b61d62a35ccadfb","side":"right"},{"sibling":"134949308b15cffd6792ee2cf678119af34d69a64764d7c89cd47573c94e1cda","side":"left"},{"sibling":"debbc1a6232ea7970009b91bdc2345041b2de5ac59551f955855d579001e512c","side":"right"},{"sibling":"216869846f40bd905626884f58cb67b9019e488b3656946a7808c436ab7339ac","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"e734b0c6d6d13acb5f4cf00367b3913e5bbf1aa717377aa4e4820c6de24b7673","side":"right"},{"sibling":"4bbb7f78e96179bb9cdd06d7207b66b3503ab68e4880438263025b04ebe8f7ec","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":149835,"merkle_root":"51484a548bc0cf3d178eec868e98935c87f0aa83369143b7c96b048585e5ba01","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260525T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-25T05:37:33Z","sig_algorithm":"ed25519","signature":"99a657e53a015ace0bade5d7fbb3f60f950b6d1e1128251a63afcc454a492422cae5efdc0c18503b4f7e62f371bd48f2889be78d9048c4681d6c1e73f754d705","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_4dcb868bcd9be8646ead6cb9fd999b7d02dad379acebf3fe837c12759efa1e01"}}