arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1601.07358quant-phcs.AIcs.LG
收藏

量子机器学习与情景任务和决策游戏的辉光

Quantum machine learning with glow for episodic tasks and decision games

Institut für Theoretische Physik, Universität Innsbruck(因斯布鲁克大学理论物理研究所)

Jens Clausen, Hans J. Briegel

摘要:

我们考虑一类通用的模型,其中强化学习(RL)代理通过经典信号从与外部环境的循环交互中学习。感知输入被编码为量子态,随后由代表智能体记忆的量子信道进行转换,而在信道输出处执行的测量结果决定智能体的动作。学习通过逐步修改信道特性来进行。它们由一个更新规则描述,该规则受到投影模拟(PS)模型的启发,并配备了一个辉光机制,该机制允许策略变化的反向传播,类似于RL中的资格跟踪和PS中的边缘辉光。通过这种方式,该模型将PS的特征与其作为量子系统的物理体现所提供的泛化能力相结合。我们将代理应用于入侵游戏和网格世界的各种设置,这些设置作为基本模型任务,可以与基本的经典PS代理进行直接比较。

英文摘要:

We consider a general class of models, where a reinforcement learning (RL) agent learns from cyclic interactions with an external environment via classical signals. Perceptual inputs are encoded as quantum states, which are subsequently transformed by a quantum channel representing the agent's memory, while the outcomes of measurements performed at the channel's output determine the agent's actions. The learning takes place via stepwise modifications of the channel properties. They are described by an update rule that is inspired by the projective simulation (PS) model and equipped with a glow mechanism that allows for a backpropagation of policy changes, analogous to the eligibility traces in RL and edge glow in PS. In this way, the model combines features of PS with the ability for generalization, offered by its physical embodiment as a quantum system. We apply the agent to various setups of an invasion game and a grid world, which serve as elementary model tasks allowing a direct comparison with a basic classical PS agent.

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。

↑