Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play
ICLR, Volume abs/1703.05407, 2018.
We describe a simple scheme that allows an agent to learn about its environment in an unsupervised manner. Our scheme pits two versions of the same agent, Alice and Bob, against one another. Alice proposes a task for Bob to complete; and then Bob attempts to complete the task. In this work we will focus on two kinds of environments: (near...More
PPT (Upload PPT)