{"_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_4dbc2cb9d94db6c0182afbc794c3bc6b48a07ce39feb25d7574212eefcddc1f7","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_4dbc2cb9d94db6c0182afbc794c3bc6b48a07ce39feb25d7574212eefcddc1f7","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"bba04bd8565b40e45749ed799c6ecf0fe4dcd30684fd4de5af329cc9d2172279","published":"Fri, 26 Jun 2026 00:00:00 -0400","receipt_hash":"bba04bd8565b40e45749ed799c6ecf0fe4dcd30684fd4de5af329cc9d2172279","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":"bba04bd8565b40e45749ed799c6ecf0fe4dcd30684fd4de5af329cc9d2172279","observed_at":"2026-06-26T04:43:58.168958Z","parent_run_hash":"9459505a803125e4b968df08c74ed0054a2aafd44e4e1a036e3b0709a8a65cb4","published":"Fri, 26 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:2606.26397v1 Announce Type: cross \nAbstract: Real-world decision-making often requires balancing multiple conflicting objectives, a challenge that standard Reinforcement Learning (RL) frequently addresses by aggregating rewards into a single scalar signal. While effective for simple tasks, this approach often fails to capture the full spectrum of optimal trade-offs, known as the Pareto frontier. In this paper, we introduce a novel preference-conditioned Bellman operator, motivated from the Chebyshev scalarization, designed to compute deterministic Pareto-optimal policies for Multi-Objective Markov Decision Processes (MOMDPs). We prove that this operator satisfies an enveloping property, where the estimated value functions upper-bound the true Pareto frontier, and demonstrate that it monotonically converges to a coverage set of this frontier. Furthermore, we also show how to extract deterministic policies from these converged Q-estimates. This ensures the agent can recover a polic","title":"Deterministic Pareto-Optimal Policy Synthesis for Multi-Objective Reinforcement Learning","url":"https://arxiv.org/abs/2606.26397","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.26397v1 Announce Type: cross \nAbstract: Real-world decision-making often requires balancing multiple conflicting objectives, a challenge that standard Reinforcement Learning (RL) frequently addresses by aggregating rewards into a single scalar signal. While effective for simple tasks, this approach often fails to capture the full spectrum of optimal trade-offs, known as the Pareto frontier. In this paper, we introduce a novel preference-conditioned Bellman operator, motivated from the Chebyshev scalarization, designed to compute deterministic Pareto-optimal policies for Multi-Objective Markov Decision Processes (MOMDPs). We prove that this operator satisfies an enveloping property, where the estimated value functions upper-bound the true Pareto frontier, and demonstrate that it monotonically converges to a coverage set of this frontier. Furthermore, we also show how to extract deterministic policies from these converged Q-estimates. This ensures the agent can recover a polic","title":"Deterministic Pareto-Optimal Policy Synthesis for Multi-Objective Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-26T04:43:58Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.26397"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:6c570ca53077a1f9fc27326a7bc200a62f0caf8af0dd1110c57ad72496c1eed9be7a97ccd67807f116ca056e770d28b11f4ed31e0eaeb02fc4e6294ce55b2f00","signer":"crovia.substrate","subject":{"observed_at":"2026-06-26T04:43:58Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.26397"},"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":"45061cca0b5ffba2039716aaadf0b956f832a736a5b730fcf4db8e82180fbad5","leaf_index":251103,"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":"c7cede5368cbde2ce5d88af8878aa488257898552d9f32a3c0061d87ed448244","side":"left"},{"sibling":"86e6fc38f683678e82a4b97d42b50b473b479e926c63c800461b511d4a7b6f00","side":"left"},{"sibling":"2265a6fed1e7ac08c8368c48d29f915175ee30645e5a02435d5d04602359b567","side":"left"},{"sibling":"28fec571a8b259b2d3e5f5050f7044a1d215ee55a86f8828accda075eac7a0bf","side":"left"},{"sibling":"33ac18fd02da741815bcd8a70e9de6248946a2e8385c7c77d02a89998fb38095","side":"left"},{"sibling":"888064c11f1cc56d64274311888a2a8db7499be3e2b85f9e56c94d171eaf0c5d","side":"right"},{"sibling":"f9190af89759db1d872794d338826ddd18310851f89900539ca641d4cae8ad95","side":"left"},{"sibling":"762a50202e5bb846bfb5afec2f3cc80d9313546598c6c53f53acc51c6325b763","side":"left"},{"sibling":"e276c2896e885a069398e8350a2d9aae49ed0ab34771e352045341312283b40a","side":"right"},{"sibling":"b6709caadc8510310ee2ec0b66d1058fcad31c91c65cc2bad6f46a693d553580","side":"right"},{"sibling":"a72c3b8804a37d1a9d18e02e6fdb048bc8ea6b0746909cd2de10bdbabc793737","side":"left"},{"sibling":"803703dc2c50a646fa77b57c0056e9a5126611ba4bcde0d6013ccd6b2d44bdbf","side":"right"},{"sibling":"e78f244b1b8df6d5e3fdc6dd76b5c27d4e6fe3b93b8cd61355497b63d7e4cfe8","side":"left"},{"sibling":"6167cb552ed6871fbf0afcf3db01d1017af7d472b136fcbe5404d1df09f41cc1","side":"right"},{"sibling":"f29798d8bb6aa9900eab878992d9ff0c53266debd87472f31ab26a6a3fb55880","side":"left"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"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":251380,"merkle_root":"e042805d07cd8dc777d49695ad78b8d4ec9721df271ff0245d7706773c30b4a5","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260626T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-26T05:37:59Z","sig_algorithm":"ed25519","signature":"c68a6e827804771acd244208495c5e35c6f417307db3c76192f038dedaa5b5f86e019074a3bea353357ff7457924c4f7907832638bb9a4d3d18e7a7f50c6a10b","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_4dbc2cb9d94db6c0182afbc794c3bc6b48a07ce39feb25d7574212eefcddc1f7"}}