Reviews: Recurrent World Models Facilitate Policy Evolution

Summary: This paper proposes a new way to develop a world model for reinforcement learning. The focus is on the encoding of the visual world, coupled with a world model that learns based on the compressed representation. The world model is a recurrent version of Bishop's (1995, neural networks book, chapter 6) mixture of gaussians network. That network outputs the weights of an MOG (using softmax), the means of the gaussians (linear outputs), and the variance (modeled as e var, so it is a scale parameter). I had not seen a recurrent version of this network before.