You never know what you're going to get with CES. Of course, we knew we'd hear a lot about AI -- check -- and that there'd be announcements of new CPUs and GPUs -- also check. But you just never know how the all the pomp and hoo-ha of this annual mega tech event is going to pay off in the real-world, for regular consumers. Does the average PC user have something to be excited about now that the veil has come off of this year's product launches? If the PCWorld staff is any indication, the answer is yes!

This paper investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with learned models is often worse than model-free alternatives, such as Double DQN, even though the former uses significantly more memory and computation. The fundamental problem is that learned models can be inaccurate and often generate invalid states, especially when iterated many steps. In this paper, we avoid this limitation by constraining background planning to a set of (abstract) subgoals and learning only local, subgoal-conditioned models. This goal-space planning (GSP) approach is more computationally efficient, naturally incorporates temporal abstraction for faster long-horizon planning and avoids learning the transition dynamics entirely. We show that our GSP algorithm can propagate value from an abstract space in a manner that helps a variety of base learners learn significantly faster in different domains.

Compared to invasive Brain-Computer Interfaces (BCI), non-invasive BCI systems based on Electroencephalogram (EEG) signals have not been applied successfully for complex control tasks. In the present study, however, we demonstrate this is possible and report on the interaction of a human subject with a complex real device: a pinball machine. First results in this single subject study clearly show that fast and well-timed control well beyond chance level is possible, even though the environment is extremely rich and requires complex predictive behavior. Using machine learning methods for mental state decoding, BCI-based pinball control is possible within the first session without the necessity to employ lengthy subject training. While the current study is still of anecdotal nature, it clearly shows that very compelling control with excellent timing and dynamics is possible for a non-invasive BCI.

Pong: a game so simple a bundle of lab-grown brain cells could play it. This might sound like a low blow, but it's true – last month, Australia-based startup Cortical Labs challenged its creation DishBrain, a biological computer chip that uses a combination of living neurons and silicon, to play the early console classic. The game – a 2D version of table tennis where players control a rectangle "paddle", moving it up and down to rally a ball – ran in the background, wired up to the DishBrain. Electrical stimulations were fed into the cells to represent the placement of the paddle and feedback was pinged when the ball was hit or missed. The scientists then measured the DishBrain's response, observing that it expended more or less energy depending on the position of the ball.

Today's video games may boast photorealistic graphics, surround sound and worldwide multiplayer support, but many still long for the days when games were simple. You know, when a game didn't require more than a joystick and a button or two? Perhaps it's no surprise, many are buying cabinets for the home, including replicas of classic coin-operated ("coin-op") games and pinball machines. "Simple games that are'quick to learn but difficult to master' have a special addictive quality that we tried for when designing them with our limited graphic palette," recalls Nolan Bushnell, who established Atari and Pong in the '70s, and shortly thereafter, founded Chuck E. Cheese (smartly, as a distribution channel for Atari games). "Often games are for turning off your mind and entering kind of a Zen state."

Compared to invasive Brain-Computer Interfaces (BCI), non-invasive BCI systems based on Electroencephalogram (EEG) signals have not been applied successfully for complex control tasks. In the present study, however, we demonstrate this is possible and report on the interaction of a human subject with a complex real device: a pinball machine. First results in this single subject study clearly show that fast and well-timed control well beyond chance level is possible, even though the environment is extremely rich and requires complex predictive behavior. Using machine learning methods for mental state decoding, BCI-based pinball control is possible within the first session without the necessity to employ lengthy subject training. While the current study is still of anecdotal nature, it clearly shows that very compelling control with excellent timing and dynamics is possible for a non-invasive BCI.

Dead Rising 4 released this week, and that's (as far as I can remember) the last big tentpole of 2016. Time for everyone to pick out their Game of the Year lists and settle in for a nice winter's nap--and maybe a chance to catch up on your backlog, finally. This week Battlefield 1 adds a Grenade Crossbow, Fallout gets the pinball treatment, someone builds an Atari 2600 in Minecraft, and Sean Bean finds out he died in the Civilization VI trailer. Before the onslaught of paid Battlefield 1 DLC starts flooding out, DICE is giving away a map to everyone for free. Starting December 20 (or December 13 if you preordered), you'll be able to play Giant's Shadow, which looks like it takes place next to a crashed zeppelin.