An AI with Imagination

Google's DeepMind creates an AI with 'imagination'

The AI firm is developing algorithms that simulate the human ability to construct plans   By Libby Plummer

 " ... The real world is complex, rules are not so clearly defined and unpredictable problems often arise," explain the DeepMind researchers in a blog post. "Even for the most intelligent agents, imagining in these complex environments is a long and costly process."

The researchers have developed "imagination-augmented agents" (I2As) – a neural network that learns to extract information that might be useful for future decisions, while ignoring anything irrelevant. These I2As can learn different strategies to construct plans, choosing from a broad spectrum of strategies.

"This work complements other model-based AI systems, like AlphaGo, which can also evaluate the consequences of their actions before they take them," the DeepMind research team told WIRED.

"What differentiates these agents is that they learn a model of the world from noisy sensory data, rather than rely on privileged information such as a pre-specified, accurate simulator. Imagination-based approaches are particularly helpful in situations where the agent is in a new situation and has little direct experience to rely on, or when its actions have irreversible consequences and thinking carefully is desirable over spontaneous action." .... "