Learning from Demonstration

Unsupervised Hierarchical Skill Discovery
We consider the problem of unsupervised skill segmentation and hierarchical structure discovery in reinforcement learning. While recent …
PDF Cite Code Project
A Non-linear Manifold Alignment Approach to Robot Learning from Demonstrations
The number and variety of robots active in real-world environments are growing, as well as the skills they are expected to acquire, and …
PDF Cite
Trajectory Learning from Human Demonstrations via Manifold Mapping
This work proposes a framework that enables arbitrary robots with unknown kinematics models to imitate human demonstrations to acquire …
PDF Cite
Nonparametric Bayesian Reward Segmentation for Skill Discovery Using Inverse Reinforcement Learning
We present a method for segmenting a set of unstructured demonstration trajectories to discover reusable skills using inverse …
PDF Cite Project