Learning the Arrow of Time for Problems in Reinforcement Learning
international conference on learning representations, 2020.
Keywords:Arrow of Time Reinforcement Learning AI-Safety
We humans have an innate understanding of the asymmetric progression of time, which we use to efficiently and safely perceive and manipulate our environment. Drawing inspiration from that, we approach the problem of learning an arrow of time in a Markov (Decision) Process. We illustrate how a learned arrow of time can capture salient info...More