Keywords: self-supervision, autonomous learning, object-centric representations, visual reinforcement learning
Abstract: Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky challenge for any autonomous agent. Previous methods have used variational autoencoders to encode a scene into a low-dimensional vector that can be used as a goal for an agent to discover new skills. Nevertheless, in compositional/multi-object environments it is difficult to disentangle all the factors of variation into such a fixed-length representation of the whole scene. We propose to use object-centric representations as a modular and structured observation space, which is learned with a compositional generative world model. We show that the structure in the representations in combination with goal-conditioned attention policies helps the autonomous agent to discover and learn useful skills. These skills can be further combined to address compositional tasks like the manipulation of several different objects.
One-sentence Summary: The combination of object-centric representations and goal-conditioned attention policies helps autonomous agents to learn useful multi-task policies in visual multi-object environments
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Code: [![github](/images/github_icon.svg) martius-lab/SMORL](https://github.com/martius-lab/SMORL)