Planning from Pixels in Atari with Learned Symbolic Representations

Understand

Width-based planning methods have been shown to yield state-of-the-art performance in the Atari 2600 domain using pixel input.

• One successful approach, RolloutIW, represents states with the B-PROST boolean feature set.
• An augmented version of RolloutIW, $\pi$-IW, shows that learned features can be competitive with handcrafted ones for width-based search.
• In this paper, we leverage variational autoencoders (VAEs) to learn features directly from pixels in a principled manner, and without supervision.