International Business Machines Corporation

University of Illinois

Yunan Ye

Jinjun Xiong

Yada Zhu

Pin-Yu Chen

Kumar Bhaskaran

Bo Li

A processor training a reinforcement learning model can include receiving a first dataset representing an observable state in reinforcement learning to train a machine to perform an action. The processor receives a second dataset. Using the second dataset, the processor trains a machine learning classifier to make a prediction about an entity related to the action. The processor extracts an embedding from the trained machine learning classifier, and augments the observable state with the embedding to create an augmented state. Based on the augmented state, the processor trains a reinforcement learning model to learn a policy for performing the action, the policy including a mapping from state space to action space.

Growing community of inventors

Hangzhou, China

Yunan Ye