人工智能的投影模拟
Projective simulation for artificial intelligence
摘要：
我们提出了一个学习代理的模型，其与环境的交互是由基于模拟的投影，它允许代理项目本身到未来的情况下，它采取实际行动之前。投射模拟基于在片段网络中的随机行走，片段是情景记忆的基本片段。剪辑的网络动态地变化，这是由于新的感知输入和由于模拟过程的某些组成原则。在模拟过程中，剪辑被筛选出触发代理实际动作的特定特征。该计划是不同于其他的，计算，模拟的概念，它提供了一个体现认知科学方法的智能行动和学习的新元素。我们的模型为量子力学操作的推广提供了一条自然的途径，并将强化学习和量子计算领域联系起来。
英文摘要：
We propose a model of a learning agent whose interaction with the environment is governed by a simulation-based projection, which allows the agent to project itself into future situations before it takes real action. Projective simulation is based on a random walk through a network of clips, which are elementary patches of episodic memory. The network of clips changes dynamically, both due to new perceptual input and due to certain compositional principles of the simulation process. During simulation, the clips are screened for specific features which trigger factual action of the agent. The scheme is different from other, computational, notions of simulation, and it provides a new element in an embodied cognitive science approach to intelligent action and learning. Our model provides a natural route for generalization to quantum-mechanical operation and connects the fields of reinforcement learning and quantum computation.
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。
