- Student First Author: Yes
- Keywords: Intrinsic motivation, curriculum learning, developmental learning, reinforcement learning
- Previously Published: Recently accepted at ECML 2020
- Abstract: Taking inspiration from developmental learning, we present a novel reinforcement learning architecture which hierarchically learns and represents self-generated skills in an end-to-end way. With this architecture, an agent focuses only on task-rewarded skills while keeping the learning process of skills bottom-up. This bottom-up approach allows to learn skills that 1- are transferable across tasks, 2- improves exploration when rewards are sparse. To do so, we combine a previously defined mutual information objective with a novel curriculum learning algorithm, creating an unlimited and explorable tree of skills. We test our agent on simple gridworld environments to understand and visualize how the agent distinguishes between its skills. Then we show that our approach can scale on more difficult MuJoCo environments in which our agent is able to build a representation of skills which improve over a baseline both transfer learning and exploration when rewards are sparse.
- TL;DR: ELSIM autonomously builds a tree of intrinsically learned skills in order to solve extrinsic tasks in an end-to-end way while promoting exploration and transfer learning.