Timezone: »

 
Poster
Learning Retrospective Knowledge with Reverse Reinforcement Learning
Shangtong Zhang · Vivek Veeriah · Shimon Whiteson

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #557
in Poster Session 2 »

We present a Reverse Reinforcement Learning (Reverse RL) approach for representing retrospective knowledge. General Value Functions (GVFs) have enjoyed great success in representing predictive knowledge, i.e., answering questions about possible future outcomes such as “how much fuel will be consumed in expectation if we drive from A to B?”. GVFs, however, cannot answer questions like “how much fuel do we expect a car to have given it is at B at time t?”. To answer this question, we need to know when that car had a full tank and how that car came to B. Since such questions emphasize the influence of possible past events on the present, we refer to their answers as retrospective knowledge. In this paper, we show how to represent retrospective knowledge with Reverse GVFs, which are trained via Reverse RL. We demonstrate empirically the utility of Reverse GVFs in both representation learning and anomaly detection.

Author Information

Shangtong Zhang (University of Oxford)
Vivek Veeriah (University of Michigan)
Shimon Whiteson (University of Oxford)

More from the Same Authors