Curiosity-Driven Exploration by Self-Supervised Prediction

In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agent's ability to predict the consequence of its own actions in a visual feature space learned by a self-supervised inverse dynamics model. Our formulation scales to high-dimensional continuous state spaces like images, bypasses the difficulties of directly predicting pixels, and, critically, ignores the aspects of the environment that cannot affect the agent. The proposed approach is evaluated in…

• NS
  National Science Foundation

  Awards: IIS-1212798, IIS-1427425, 1427425, 1212798, 1536003
• N
  Nvidia
• MU
  Multidisciplinary University Research Initiative
• OO
  Office of Naval Research

  Awards: N00014-14-1-0671, N00014