arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.08271cs.AIcs.LG
收藏

Act-Then-Measure:基于主动测量的部分可观测环境下的强化学习

Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring

Radboud University(拉德堡德大学);Nijmegen Institute for Computing and Information Sciences(奈梅亨计算与信息科学研究所)

Merlijn Krale, Thiago D. Simão, Nils Jansen

摘要:

我们研究马尔可夫决策过程(MDP),代理人直接控制何时以及如何收集信息,作为正式的行动或有无噪声可观察MDP(ACNO-MPD)。在这些模型中,动作由两个部分组成:影响环境的控制动作和影响代理可以观察到的内容的测量动作。为了解决ACNO-MDP,我们引入了行动然后测量(ATM)启发式算法,该算法假设我们在选择控制动作时可以忽略未来状态的不确定性。我们展示了如何遵循这种启发式可能会导致更短的政策计算时间,并证明了启发式所产生的性能损失的约束。为了决定是否采取度量行动,我们引入了度量值的概念。我们开发了一种基于ATM启发式的强化学习算法,使用适合部分可观察域的Dyna-Q变体,并在一些部分可观察的环境中展示了其优越的性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑