Following Instructions by Imagining and Reaching Visual Goals

摘要

While traditional methods for instruction-following typically assume prior linguistic and perceptual knowledge, many recent works in reinforcement learning (RL) have proposed learning policies end-to-end, typically by training neural networks to map joint representations of observations and instructions directly to actions. In this work, we present a novel framework for learning to perform temporally extended tasks using spatial reasoning in the RL framework, by sequentially imagining visual goals and choosing appropriate actions to fulfill imagined goals. Our framework operates on raw pixel images, assumes no prior linguistic or perceptual knowledge, and learns via intrinsic motivation and a single extrinsic reward signal measuring task completion. We validate our method in two environments with a robot arm in a simulated interactive 3D environment. Our method outperforms two flat architectures with raw-pixel and ground-truth states, and a hierarchical architecture with ground-truth states on object arrangement tasks.