智能体 Agent ; intelligent agent ; Agent-Oriented ; GIS intelligent agent
智能主体 agent
多智能体 Agent ; multi-agent ; Multi-Agent System
多智能体系统 Multi-agent system ; Multi-agent Systems
移动智能体 Mobile Agent
云智能体 Cloud Agent
智能体技术 Intelligent Agent Technologies
基于智能体的制造系统 Agent-based Manufacturing system
基于智能体 agent-based
空间智能体 Geo-Agent
Once these different functions (such as the probability distribution) are learned, the correct action to take is simply a matter of deciding which action maximizes the "expected utility" of the agent.
一旦这些不同的函数(例如概率分布)都被掌握,智能体就会很容易判断哪一种行为会让预期效用最大化,并据此选择正确的行为。
The idea is that the computer (or the "agent") can get a certain amount of value from performing some actions.
它为计算机(或“智能体”,即Agent,译者注)执行一项操作赋予某些分值。
Reinforcement learning based on Markov decision process is a way of on-line learning, which can be applied to single agent environment.
基于马尔科夫过程的强化学习作为一种在线学习方式,能够很好地应用于单智能体环境中。
应用推荐