{"_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_723d5219abc3126a9d136bb9564c7b069e7629b7d377ab4e30f2abf6561a0495","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_723d5219abc3126a9d136bb9564c7b069e7629b7d377ab4e30f2abf6561a0495","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"11d389990edaf181763839deab8f221e2d175c83ebad9b8b12a5b2a48bbbb563","published":"Tue, 02 Jun 2026 00:00:00 -0400","receipt_hash":"11d389990edaf181763839deab8f221e2d175c83ebad9b8b12a5b2a48bbbb563","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":"11d389990edaf181763839deab8f221e2d175c83ebad9b8b12a5b2a48bbbb563","observed_at":"2026-06-02T04:43:38.825628Z","parent_run_hash":"c2a9665c814770d56765bb764e6a6c7e4fa7d4e9708e157ca0f7440c89927d54","published":"Tue, 02 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:2512.18336v2 Announce Type: replace-cross \nAbstract: This paper explores the impact of dynamic entropy tuning in Reinforcement Learning (RL) algorithms that train a stochastic policy. Its performance is compared against algorithms that train a deterministic one. Stochastic policies optimize a probability distribution over actions to maximize rewards, while deterministic policies select a single deterministic action per state. The effect of training a stochastic policy with both static entropy and dynamic entropy and then executing deterministic actions to control the quadcopter is explored. It is then compared against training a deterministic policy and executing deterministic actions. For the purpose of this research, the Soft Actor-Critic (SAC) algorithm was chosen for the stochastic algorithm while the Twin Delayed Deep Deterministic Policy Gradient (TD3) was chosen for the deterministic algorithm. The training and simulation results show the positive effect the dynamic entrop","title":"Dynamic Entropy Tuning in Reinforcement Learning Low-Level Quadcopter Control: Stochasticity vs Determinism","url":"https://arxiv.org/abs/2512.18336","vendor":"arxiv_cs_ai"},"summary":"arXiv:2512.18336v2 Announce Type: replace-cross \nAbstract: This paper explores the impact of dynamic entropy tuning in Reinforcement Learning (RL) algorithms that train a stochastic policy. Its performance is compared against algorithms that train a deterministic one. Stochastic policies optimize a probability distribution over actions to maximize rewards, while deterministic policies select a single deterministic action per state. The effect of training a stochastic policy with both static entropy and dynamic entropy and then executing deterministic actions to control the quadcopter is explored. It is then compared against training a deterministic policy and executing deterministic actions. For the purpose of this research, the Soft Actor-Critic (SAC) algorithm was chosen for the stochastic algorithm while the Twin Delayed Deep Deterministic Policy Gradient (TD3) was chosen for the deterministic algorithm. The training and simulation results show the positive effect the dynamic entrop","title":"Dynamic Entropy Tuning in Reinforcement Learning Low-Level Quadcopter Control: Stochasticity vs Determinism","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-02T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2512.18336"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:4d9486a1a659e34582f66b4c83ef2d93e952eb4ff3e195da2e802ae158fae9ce4c833b0dc0b8fbb8420debc21536fc76976d2048b9ecc2c2a83332e0404be902","signer":"crovia.substrate","subject":{"observed_at":"2026-06-02T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2512.18336"},"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":"09670ee3cd8d5835325734d7172af685eb43af900b507e01bf4b8f4ef9e47891","leaf_index":205918,"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":"f8ae28f3f26c7fbf115ccaed2059d55cbaf1a3f1668b1d56858a29d7551bdf1f","side":"right"},{"sibling":"64b3bb1b64f56d5365fbbdc718a3abd3abcc2310705d2f0c28b7f15996c30c5c","side":"left"},{"sibling":"730c52f18567a112197594d2a2a520ee151eed1b9c04e0022b3d7eab71b7e6d0","side":"left"},{"sibling":"339c52b7ad436b2bf929f9d09175907a20f52b1c1b2c23afcf0b147ff8296d83","side":"left"},{"sibling":"aab09d679873778a0fc33b64a28ed3ce6be6df767720bc775fca5ed507a94893","side":"left"},{"sibling":"e92b8ea42f6bc163f81eddcf5a1f43bf23f994c592c5c1fa0ab7ca7ac0791b22","side":"right"},{"sibling":"e3079b690878ce30b8ca3786d84b9c0a1891426d146e638fe7ca9df8dcb74e02","side":"left"},{"sibling":"a5c0411da65d36a27f4e797deeace23f77314552708425e4e91c3ebf671bc23b","side":"right"},{"sibling":"6ac554ede1f78dc3a28ebe5e1155c2b9c258b71805fdd7ad2ec992697f3ccd0c","side":"right"},{"sibling":"5e1949edfad76bc6a73d008dc8be8a0c6fe4a7fb64c8beaf70e5023ca11d35e0","side":"right"},{"sibling":"e4bd1aaaf3f336d9b072b4d1fc234246fc3cf2874ca873b7741c03eaf97911f2","side":"left"},{"sibling":"e6adead8216db4cae92f0a036d53baebf30eed95a99c0d10758aa75bb7780f2f","side":"right"},{"sibling":"1acc2b7ff453ffd8c97b80ae4db5358780f0c6796874fd75403791dbe99f8cd7","side":"right"},{"sibling":"24d1bb4b13e0e46131b27b70a48e65fcf4e2e14b95e3bb83ade821e9df530f6b","side":"left"},{"sibling":"5f86f58c28b1a86ae06dfff4666bb9fba8866021a81fd4f1d200aa9af4722dfb","side":"right"},{"sibling":"f6cc6f94f6944ae21390afc65ac9e91dc31f84ee6e060681bba5ae08058294bd","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":206226,"merkle_root":"d2a6d32b13cbf343fb143b21a756d0533864ae6577a376ee84ba867b949207ec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260602T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-02T05:37:46Z","sig_algorithm":"ed25519","signature":"abd9956cfb19dd1fb8142c46a220bac2514848c6abb0e79b8b0940206cc3ebb00894d4daaf9f786427f82a7cc12482e7fda79054ebb06bceaa9b4b97e23fb30e","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_723d5219abc3126a9d136bb9564c7b069e7629b7d377ab4e30f2abf6561a0495"}}