{"_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_d170bb9d6c368d1e521c7c014426b5a92b18f3a4a6da17627571d94e37882c7b","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_d170bb9d6c368d1e521c7c014426b5a92b18f3a4a6da17627571d94e37882c7b","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"b9053aeff63742233be6603f69f1c1419d151e8cad963dea73e1fadf7ec399c6","published":"Thu, 02 Jul 2026 00:00:00 -0400","receipt_hash":"b9053aeff63742233be6603f69f1c1419d151e8cad963dea73e1fadf7ec399c6","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":"b9053aeff63742233be6603f69f1c1419d151e8cad963dea73e1fadf7ec399c6","observed_at":"2026-07-02T04:43:28.872255Z","parent_run_hash":"9f528c2a80e5b201c2a66ae885c05dd596ad2c3532bb4c6809c7c9704d10e650","published":"Thu, 02 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:2607.00642v1 Announce Type: new \nAbstract: Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing to robotics to foundation models. Through trial-and-error, these AI systems typically learn one, near-optimal behavior to solve their tasks. However, there are many use cases in which one would like to assert some level of control, preferably in real time, over how the task is solved. We refer to these modifications of a core task as styles. We combine universal value function approximators (UVFAs) with carefully selected training scenarios, learning algorithms, and data augmentation to create a framework for coaching agents that exhibit styles in complex domains. We demonstrate the framework's application in the AAA video games Horizon Forbidden West and Gran Turismo, and in an open-source humanoid test domain. Despite the different nature of the domains -- car racing, stylized game com","title":"Coachable agents for interactive gameplay","url":"https://arxiv.org/abs/2607.00642","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.00642v1 Announce Type: new \nAbstract: Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing to robotics to foundation models. Through trial-and-error, these AI systems typically learn one, near-optimal behavior to solve their tasks. However, there are many use cases in which one would like to assert some level of control, preferably in real time, over how the task is solved. We refer to these modifications of a core task as styles. We combine universal value function approximators (UVFAs) with carefully selected training scenarios, learning algorithms, and data augmentation to create a framework for coaching agents that exhibit styles in complex domains. We demonstrate the framework's application in the AAA video games Horizon Forbidden West and Gran Turismo, and in an open-source humanoid test domain. Despite the different nature of the domains -- car racing, stylized game com","title":"Coachable agents for interactive gameplay","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-02T04:43:28Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.00642"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ffc86065771869527aa1559f88dd62f726a8fbdd85c91f7c9a8d0ea79d87ecfb11bc118a1f1963a864ae039b3107f95416dcc090fe0d2fc9118bed02983ac307","signer":"crovia.substrate","subject":{"observed_at":"2026-07-02T04:43:28Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.00642"},"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":"547e7957b3b4b7709baad7277812d8c1c048a8ce8806e18b77c10e26a7cb4175","leaf_index":271931,"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":"b506acdc7f5f27d370cb48e645e0e33f11847f84fae41f4649e9003d9c7517eb","side":"left"},{"sibling":"a6a26190557afddbecf6bbbb3dfcafae228e7591fc7af2b4f8833b1558ea3645","side":"left"},{"sibling":"411f8b17197fcbce2e3f65bb779a3092f0bc11c5e21b9f1c8fd4e129095b1353","side":"right"},{"sibling":"978485cd24a81f3ad962245a02b89915a8e001aa5c76348f9f6c4eb4c1ab34cf","side":"left"},{"sibling":"4f906ab66b2d5de4b3cb2cb08706d962a691a84c8e9e1f6e2a599e21d631c9d3","side":"left"},{"sibling":"fe85befc120b37479936768544f368e6794f3c12abc9a274e87c6c02315c3c3f","side":"left"},{"sibling":"7f612213bd4a57a2ce8be6dac18395d700b47185ca62dde9c31e6ad7095ce490","side":"right"},{"sibling":"245706846217c65709d33d0c2ef53806eee8ea674294e4e08c1d4f19cee09ac7","side":"right"},{"sibling":"155ae596a5c6a5260be50ff412642fbd25f4587b43e04c56950c1dc544719be1","side":"right"},{"sibling":"4cfdd7f7072619c015edc477162c2cf29c6f70370acb8dbddf1eb590876d82fe","side":"left"},{"sibling":"43990c9db8fcb3172d821965dfac69152981af4108b8dc87bd32f15c0e56f4cf","side":"left"},{"sibling":"15dbacc2e5845fe3bb835797bb7647ab6f091e79adadd39f40c636980716c622","side":"right"},{"sibling":"7ecc1d0d471643b88d886db58cb02a77af4d1495674760c3867834550b143757","side":"right"},{"sibling":"8a09562f6b247c1c3cd1fea36cb3b8f1cf5c575479dd514573856a380a964bf5","side":"left"},{"sibling":"7b681d50e7d0a7b8d2a749507aed58030072539a90fab18de4f698743685cc00","side":"right"},{"sibling":"9b262645232510ff15bb7325ab858256f2914f711d2726caeafd49f5ca0fb7a9","side":"right"},{"sibling":"5bd94446b5721b713c5e4dcf4624b9bc682657ab2784af927caae7b80c297d7d","side":"right"},{"sibling":"21ac0b7091fe1133859bcd17b4f8da2fe37a2489d472dad508305740b483221b","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":272319,"merkle_root":"dd4fa4deb1f207e8a7756821b4f940f39e9f06a25e6fa8500a21dd403318a5a7","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260702T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-02T05:38:06Z","sig_algorithm":"ed25519","signature":"68eb2e3bbc0f593bea7b5c3c110c90b6f4fe4fd8277d8dee7c866ba0471c1a50684aa4539c8a493e6d9c9202d8c03f4d897a0df3477e9ecd5b0ff03eb1016f00","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_d170bb9d6c368d1e521c7c014426b5a92b18f3a4a6da17627571d94e37882c7b"}}