Shared with Dropbox

Neural networks have shown great success in everything from playing Go and Atari games to image recognition and language translation. But often overlooked is that the success of a neural network at a particular application is often determined by a series of choices made at the start of the research, including what type of network to use and the data and method used to train it. Currently, these choices - known as hyperparameters - are chosen through experience, random search or a computationally intensive search processes.In our most recent paper, we introduce a new method for training neural networks which allows an experimenter to quickly choose the best set of hyperparameters and model for the task. This technique - known as Population Based Training (PBT) - trains and optimises a series of networks at the same time, allowing the optimal set-up to be quickly found. Crucially, this adds no computational overhead, can be done as quickly as traditional techniques and is easy to integrate into existing machine…

Quantile Regression on Pong, one state CDF (x - prob, y - reward) https://t.co/AJ5bsnMGWl

A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents! - deepmind/pycolab