Sub-Task Discovery with Limited Supervision: A Constrained Clustering Approach

no code implementations • ICLR Workshop LLD 2019 • Phillip Odom, Aaron Keech, Zsolt Kira

Hierarchical reinforcement learning captures sub-task information to learn modular policies that can be quickly adapted to new tasks.

Constrained Clustering Hierarchical Reinforcement Learning +2

Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds

no code implementations • 12 Sep 2017 • Zhiyu Lin, Brent Harrison, Aaron Keech, Mark O. Riedl

We describe a method to use discrete human feedback to enhance the performance of deep learning agents in virtual three-dimensional environments by extending deep-reinforcement learning to model the confidence and consistency of human feedback.

reinforcement-learning Reinforcement Learning (RL)