We study Markov decision processes (MDPs), where agents have direct control over when and how they gather information, as formalized by action-contingent noiselessly observable MDPs (ACNO-MPDs). In these models, actions consist of two components: a control action that affects the environment, and a measurement action that affects what the agent can observe. To solve ACNO-MDPs, we introduce the act-then-measure (ATM) heuristic, which assumes that we can ignore future state uncertainty when choosing control actions. We show how following this heuristic may lead to shorter policy computation times and prove a bound on the performance loss incurred by the heuristic. To decide whether or not to take a measurement action, we introduce the concept of measuring value. We develop a reinforcement learning algorithm based on the ATM heuristic, using a Dyna-Q variant adapted for partially observable domains, and showcase its superior performance compared to prior methods on a number of partially-observable environments.

翻译：我们研究马尔可夫决策过程（MDPs），其中智能体能够直接控制信息采集的时机与方式，这通过行为依赖型无噪声可观测MDPs（ACNO-MDPs）形式化建模。在此类模型中，行动包含两个组成部分：影响环境的控制行动，以及影响智能体观测能力的测量行动。为求解ACNO-MDPs，我们提出“先行动再测量”（ATM）启发式方法，该方法假设在选择控制行动时可忽略未来状态的不确定性。我们论证遵循此启发式方法可缩短策略计算时间，并证明该方法所引发性能损失的上界。为判断是否执行测量行动，我们引入“测量价值”概念。基于ATM启发式方法，我们开发了强化学习算法，采用专为部分可观测域改进的Dyna-Q变体，并在多个部分可观测环境中展示了该算法相较于先前方法的优越性能。