Diversity is All You Need: Learning Skills without a Reward Function
Remote
Intelligent creatures can explore their environments and learn useful skills without supervision. In this talk, we will present a method, 'Diversity is All You Need' (DIAYN), for learning useful skills without a reward function. We show how pretrained skills can provide a good parameter initialization for downstream tasks, and can be composed hierarchically to solve complex, sparse reward tasks. We will then discuss a close connection between autonomous skill discovery and meta-learning. Whereas typical meta-reinforcement learning algorithms require a manually-designed family of reward functions, we show how to use DIAYN to propose tasks for meta-learning in an unsupervised manner, effectively resulting in an unsupervised meta-learning algorithm. While there has been considerable work in this area in the past few years, a number of algorithmic and theoretical questions remain open. We plan to highlight some of these challenges at the end.https://arxiv.org/abs/1802.06070https://umd.zoom.us/j/2920984437Slides and recording will be available at: https://www.cs.umd.edu/talks/rlss