"In recent years there have been many successes of using deep representations in reinforcement learning. Still, many of these applications use conventional architectures, such as convolutional networks, LSTMs, or…Read More
Abstract:
We propose a lifelong learning system that has the ability to reuse and transfer knowledge from one task to another while efficiently retaining the previously learned knowledge-base. Knowledge is…Read More
Deep reinforcement learning methods attain super-human performance in a wide range of environments. Such methods are grossly inefficient, often taking orders of magnitudes more data than humans to achieve reasonable performance.…Read More
From Authors:
"We've discovered that evolution strategies (ES), an optimization technique that's been known for decades, rivals the performance of standard reinforcement learning (RL) techniques…Read More
The paper presents he first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. It's a must read for AI scientists
From MIT Technology Review:
One set of experiments from Google’s DeepMind group suggests that what researchers are terming “learning to learn” could also help lessen the problem of machine-learning…Read More
