Teaching Artificial Agents to Understand Language by Modelling Reward.

Recent progress in Deep Reinforcement Learning has shown that agents can be taught complex behaviour and solve difficult tasks, such as playing video games from pixel observations, or mastering the game of Go without observing human games, with relatively little prior information. Building on these successes, researchers such as Hermann and colleagues have sought to apply these methods to teach - in simulation - agents to complete a variety of tasks specified by combinatorially rich instruction languages. In this talk, we discuss some of these highlights and some of the limitations which inhibit scalability of such approaches to more complex instruction languages (including natural language). Following this, we introduce a new approach, inspired by recent work in adversarial reward modelling, which constitutes a first step towards scaling instruction-conditional agent training to "real world" language, unlocking the possibility of applying these techniques within a wide range of industrial applications.