These notes are created from an implementation POV. Main contribution: Their main contribution is to learn long-horizon behaviors by propagating analytic value gradients through imagined trajectories. They show that this method gives empirically scalable results on complex control tasks. Learning long-horizon behaviors by latent imagination. Empirical performance for visual control. Algorithm:

Problem setting: The authors propose "Sentio", a Reinforcement Learning based algorithm to enhance the Forward Collision Warning (FCW) system leading to Driver-in-the-Loop FCW system. On top of considerating the threshold of time-to-crash by traditional FCW systems this algo also claims to take in account Driver's preference or mood. Change in the driver's mood over time. Aproach: To address the above challenges, Sentio:

Introduction They simultaneously train two models for generating data: A generative model G that captures the data distribution and generates new samples from that distribution. A discriminative model D that estimates the probability that a sample belongs to true data rather than Generated data. The training is carried out in such a way that both these models improve in their corresponding tasks until ideally the generated data is indistinguishable from the original training data. Summary of pre-reqs: Information theory

Introduction The authors propose a new architecture for anomaly detection in videos. Their architecture includes two main components one for spatial feature representation, and one for learning the temporal evolution of the spatial features. Principle of working The method is based on the principle that the frames containing an abnormality will be significantly different from the previous frames. Methodology Pre-processing Each frame is extracted from the raw videos and resized to 27×227.