Get the latest tech news
Deep Reinforcement Learning: Pong from Pixels (2016)
Musings of a Computer Scientist.
Compute (the obvious one: Moore’s Law, GPUs, ASICs), Data (in a nice form, not just out there somewhere on the internet - e.g. ImageNet), Algorithms (research and ideas, e.g. backprop, CNN, LSTM), and Infrastructure (software under you - Linux, TCP/IP, Git, ROS, PR2, AWS, AMT, TensorFlow, etc. On the low level the game works as follows: we receive an image frame (a 210x160x3 byte array (integers from 0 to 255 giving pixel values)) and we get to decide if we want to move the paddle UP or DOWN (i.e. a binary choice). In the case of Reinforcement Learning for example, one strong baseline that should always be tried first is the cross-entropy method (CEM), a simple stochastic hill-climbing “guess and check” approach inspired loosely by evolution.
Or read this on Hacker News
