Abstract:In many practical sequential decision-making problems, tracking the state of the environment incurs a sensing/communication/computation cost. In these settings, the agent's interaction with its environment includes the additional component of deciding when to sense the state, in a manner that balances the value associated with optimal (state-specific) actions and the cost of sensing. We formulate this as an expected discounted cost Markov Decision Process (MDP), wherein the agent incurs an additional cost for sensing its next state, but has the option to take actions while remaining `blind' to the system state. We pose this problem as a classical discounted cost MDP with an expanded (countably infinite) state space. While computing the optimal policy for this MDP is intractable in general, we derive lower bounds on the optimal value function, which allow us to bound the suboptimality gap of any policy. We also propose a computationally efficient algorithm SPI, based on policy improvement, which in practice performs close to the optimal policy. Finally, we benchmark against the state-of-the-art via a numerical case study.
| Comments: | Accepted at AISTATS 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2505.03280 [cs.LG] |
| (or arXiv:2505.03280v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2505.03280 arXiv-issued DOI via DataCite |
|
| Journal reference: | Proceedings of the 29th International Conference on Artificial Intelligence and Statistics (AISTATS 2026) |
From: Vansh Kapoor [view email]
[v1]
Tue, 6 May 2025 08:06:45 UTC (1,860 KB)
[v2]
Wed, 29 Oct 2025 06:48:01 UTC (1,789 KB)
[v3]
Tue, 14 Apr 2026 22:12:25 UTC (1,791 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。