Learning retrospective knowledge with reverse reinforcement learning

Conference item

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.

Authors: Zhang, S; Veeriah, V; Whiteson, S

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: NeurIPS
• Journal: NeurIPS Proceedings 2020
• Volume: 33
• Publication date: 2020-12-11
• Acceptance date: 2020-12-01
• Event title: 34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020)
• Event location: Online
• Event website: https://nips.cc/
• Event start date: 2020-12-06
• Event end date: 2020-12-12
• Language: English