{"paper":{"title":"AoI-MDP: An AoI Optimized Markov Decision Process (Student Abstract)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Incorporating age of information into the state space and adding a wait action lets reinforcement learning produce better policies for underwater vehicles facing observation delays.","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Guanwen Xie, Jingzehua Xu, Shuai Zhang, Xinqi Wang, Yimian Ding, Yiyuan Yang","submitted_at":"2026-05-16T03:16:50Z","abstract_excerpt":"Ocean exploration places high demands on autonomous underwater vehicles, especially when there's observation delay. We propose age of information optimized Markov decision process (AoI-MDP) to enhance underwater tasks by modeling observation delay as signal delay and including it in the state space. AoI-MDP also introduces wait time in the action space and integrates AoI with reward functions, optimizing information freshness and decision-making using reinforcement learning. Simulations show AoI-MDP outperforms the standard MDP, demonstrating superior performance, feasibility, and generalizati"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Simulations show AoI-MDP outperforms the standard MDP, demonstrating superior performance, feasibility, and generalization in underwater tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That adding age of information to the state and a wait action will produce better policies without introducing instability or requiring extensive new hyper-parameter tuning in the reinforcement learning process.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AoI-MDP integrates age of information into MDP state, action, and reward to optimize decision-making under observation delays for underwater autonomous vehicles.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Incorporating age of information into the state space and adding a wait action lets reinforcement learning produce better policies for underwater vehicles facing observation delays.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d8c18e4e2555920c764095222fddd4e2c36fd05ca2302f0a852f174281b9e6e7"},"source":{"id":"2605.16777","kind":"arxiv","version":1},"verdict":{"id":"043061db-a3d2-4dc1-809d-c2b82d14cf7d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:28:14.765743Z","strongest_claim":"Simulations show AoI-MDP outperforms the standard MDP, demonstrating superior performance, feasibility, and generalization in underwater tasks.","one_line_summary":"AoI-MDP integrates age of information into MDP state, action, and reward to optimize decision-making under observation delays for underwater autonomous vehicles.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That adding age of information to the state and a wait action will produce better policies without introducing instability or requiring extensive new hyper-parameter tuning in the reinforcement learning process.","pith_extraction_headline":"Incorporating age of information into the state space and adding a wait action lets reinforcement learning produce better policies for underwater vehicles facing observation delays."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16777/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:19.692358Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:40:53.426719Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.305472Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.440470Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"906e2927cd99a9c2102d3fb4590e1f73c983d7c1d96d59a388369d577a773b4e"},"references":{"count":19,"sample":[{"doi":"","year":null,"title":"Vol and Energy-Aware AUV-Assisted Data Collection for Internet of Underwater Things , year=","work_id":"0e9f9b37-be43-45ce-8ce1-ad96cbb60c2b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Noncooperative Mobile Target Tracking Using Multiple AUVs in Anchor-Free Environments , year=","work_id":"0e379384-e9c2-4423-be6c-3ff21929b174","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Environment and Energy-Aware AUV-Assisted Data Collection for the Internet of Underwater Things , year=","work_id":"7709ad76-03a2-4bce-a03a-127abe2f6077","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Wei, Wei and Wang, Jingjing and Du, Jun and Fang, Zhengru and Ren, Yong and Chen, C. L. Philip , journal=. Differential Game-Based Deep Reinforcement Learning in Underwater Target Hunting Task , year=","work_id":"9ccdfe31-7027-4bdb-ab62-c163dd674da5","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Reinforcement Learning and Particle Swarm Optimization Supporting Real-Time Rescue Assignments for Multiple Autonomous Underwater Vehicles , year=","work_id":"d55f0825-a67d-401c-bec6-44763a2516e6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":19,"snapshot_sha256":"9b8b8c5b8802126a61be3904fb9f2b8db36f7f2cbcdd8b36c422eebe77e90f3d","internal_anchors":1},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}