Algorithms that parse data, learn from that data, and then apply what they've learned to make informed decisions. I'm sure you are asking yourself, how can a program or algorithm make decisions and learn from data, doesn't every program need to be programmed? Not if the program was trained to learn from and adapt to data. In the case of machine learning the algorithm is not explicitly programmed, rather the model is "trained" using historical and present data in order to make future decisions and prediction. The more data available for training, the more accurate the predictions are.
Our goal is to make Deep Reinforcement Learning accessible to everyone. We introduce Surreal, an open-source, reproducible, and scalable distributed reinforcement learning framework. Surreal provides a high-level abstraction for building distributed reinforcement learning algorithms. We implement our distributed variants of PPO and DDPG in the current release. Click to see detailed documentation!
Excellent painters can use only a few strokes to create a fantastic painting, which is a symbol of human inte and art. Reversing the simulator to interpret images is also a challenging task of computer vision in recent years. In this paper, we propose a stroke-based rendering (SBR) method that combines the neural stroke renderer (NSR) and deep reinforcement learning (DRL), allowing the machine to learn the ability of deconstructing images using strokes and create amazing visual effects. Our agent is an end-to-end program that converts natural images into paintings. The training process does not require human painting experience or stroke tracking data.